Note

This page was generated from harmonization.ipynb. Interactive online version: Colab badge. Some tutorial content may look better in light mode.

Atlas-level integration of lung data#

An important task of single-cell analysis is the integration of several samples, which we can perform with scVI. For integration, scVI treats the data as unlabelled. When our dataset is fully labelled (perhaps in independent studies, or independent analysis pipelines), we can obtain an integration that better preserves biology using scANVI, which incorporates cell type annotation information. Here we demonstrate this functionality with an integrated analysis of cells from the lung atlas integration task from the scIB manuscript. The same pipeline would generally be used to analyze any collection of scRNA-seq datasets.

[1]:
%%capture
import sys

#if branch is stable, will install via pypi, else will install from source
branch = "stable"
IN_COLAB = "google.colab" in sys.modules

if IN_COLAB and branch == "stable":
    !pip install --quiet scvi-tools[tutorials]
    !pip install --quiet git+https://github.com/theislab/scib.git
elif IN_COLAB and branch != "stable":
    !pip install --quiet --upgrade jsonschema
    !pip install --quiet git+https://github.com/yoseflab/scvi-tools@$branch#egg=scvi-tools[tutorials]
    !pip install --quiet git+https://github.com/theislab/scib.git
[2]:
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np
import pandas as pd

import scanpy as sc
import scvi
import scib

sc.set_figure_params(figsize=(4, 4))

%config InlineBackend.print_figure_kwargs={'facecolor' : "w"}
%config InlineBackend.figure_format='retina'
Global seed set to 0
/usr/local/lib/python3.7/dist-packages/numba/np/ufunc/parallel.py:363: NumbaWarning: The TBB threading layer requires TBB version 2019.5 or later i.e., TBB_INTERFACE_VERSION >= 11005. Found TBB_INTERFACE_VERSION = 9107. The TBB threading layer is disabled.
  warnings.warn(problem)
[3]:
adata = sc.read(
    "data/lung_atlas.h5ad",
    backup_url="https://figshare.com/ndownloader/files/24539942",
)

Note that this dataset has the counts already separated in a layer. Here, adata.X contains log transformed scran normalized expression.

[4]:
adata
[4]:
AnnData object with n_obs × n_vars = 32472 × 15148
    obs: 'dataset', 'location', 'nGene', 'nUMI', 'patientGroup', 'percent.mito', 'protocol', 'sanger_type', 'size_factors', 'sampling_method', 'batch', 'cell_type', 'donor'
    layers: 'counts'

Dataset preprocessing#

This dataset was already processed as described in the scIB manuscript. Generally, models in scvi-tools expect data that has been filtered/aggregated in the same fashion as one would do with Scanpy/Seurat.

Another important thing to keep in mind is highly-variable gene selection. While scVI and scANVI both accomodate using all genes in terms of runtime, we usually recommend filtering genes for best integration performance. This will, among other things, remove batch-specific variation due to batch-specific gene expression.

We perform this gene selection using the Scanpy pipeline while keeping the full dimension normalized data in the adata.raw object. We obtain variable genes from each dataset and take their intersections.

[5]:
adata.raw = adata  # keep full dimension safe
sc.pp.highly_variable_genes(
    adata,
    flavor="seurat_v3",
    n_top_genes=2000,
    layer="counts",
    batch_key="batch",
    subset=True
)
/usr/local/lib/python3.7/dist-packages/scanpy/preprocessing/_highly_variable_genes.py:64: UserWarning: `flavor='seurat_v3'` expects raw count data, but non-integers were found.
  UserWarning,
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.float` is a deprecated alias for the builtin `float`. To silence this warning, use `float` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.float64` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.float` is a deprecated alias for the builtin `float`. To silence this warning, use `float` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.float64` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.float` is a deprecated alias for the builtin `float`. To silence this warning, use `float` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.float64` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.float` is a deprecated alias for the builtin `float`. To silence this warning, use `float` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.float64` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):

Important

We see a warning about the data not containing counts. This is due to some of the samples in this dataset containing SoupX-corrected counts. scvi-tools models will run for non-negative real-valued data, but we strongly suggest checking that these possibly non-count values are intended to represent pseudocounts, and not some other normalized data, in which the variance/covariance structure of the data has changed dramatically.

Integration with scVI#

As a first step, we assume that the data is completely unlabelled and we wish to find common axes of variation between the two datasets. There are many methods available in scanpy for this purpose (BBKNN, Scanorama, etc.). In this notebook we present scVI. To run scVI, we simply need to:

  • Register the AnnData object with the correct key to identify the sample and the layer key with the count data.

  • Create an SCVI model object.

[6]:
scvi.model.SCVI.setup_anndata(adata, layer="counts", batch_key="batch")
/usr/local/lib/python3.7/dist-packages/scvi/data/fields/_layer_field.py:79: UserWarning: adata.layers[counts] does not contain unnormalized count data. Are you sure this is what you want?
  f"{logger_data_loc} does not contain unnormalized count data. "

We note that these parameters are non-default; however, they have been verified to generally work well in the integration task.

[7]:
vae = scvi.model.SCVI(adata, n_layers=2, n_latent=30, gene_likelihood="nb")

Now we train scVI. This should take a couple of minutes on a Colab session

[8]:
vae.train()
GPU available: True, used: True
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]
Epoch 246/246: 100%|██████████| 246/246 [09:19<00:00,  2.27s/it, loss=553, v_num=1]

Once the training is done, we can evaluate the latent representation of each cell in the dataset and add it to the AnnData object

[9]:
adata.obsm["X_scVI"] = vae.get_latent_representation()

Finally, we can cluster the dataset and visualize it the scVI latent space.

[12]:
sc.pp.neighbors(adata, use_rep="X_scVI")
sc.tl.leiden(adata)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/np/arrayobj.py:3836: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  NPY_TY = getattr(types, "int%s" % (8 * np.dtype(np.int).itemsize))
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
sys:1: ResourceWarning: unclosed socket <zmq.Socket(zmq.PUSH) at 0x7fe6a9adf7c0>
ResourceWarning: Enable tracemalloc to get the object allocation traceback
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
sys:1: ResourceWarning: unclosed socket <zmq.Socket(zmq.PUSH) at 0x7fe6a683dbb0>
ResourceWarning: Enable tracemalloc to get the object allocation traceback
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/consts.py:114: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  return getattr(value, expr.attr)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:2061: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  defn = getattr(defn, x, False)
/usr/local/lib/python3.7/dist-packages/numba/core/typing/context.py:338: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  attrval = getattr(typ.pymod, attr)
/usr/local/lib/python3.7/dist-packages/numba/core/typing/context.py:338: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  attrval = getattr(typ.pymod, attr)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/typing/context.py:338: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  attrval = getattr(typ.pymod, attr)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1525: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  if (hasattr(numpy, value)
/usr/local/lib/python3.7/dist-packages/numba/core/ir_utils.py:1526: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  and def_val == getattr(numpy, value)):

To visualize the scVI’s learned embeddings, we use the pymde package wrapperin scvi-tools. This is an alternative to UMAP that is GPU-accelerated.

[13]:
from scvi.model.utils import mde
import pymde
adata.obsm["X_mde"] = mde(adata.obsm["X_scVI"])
[14]:
sc.pl.embedding(
    adata,
    basis="X_mde",
    color=["batch", "leiden"],
    frameon=False,
    ncols=1,
)
../../_images/tutorials_notebooks_harmonization_22_0.png

Because this data has been used for benchmarking, we have access here to curated annotations. We can use those to assess whether the integration worked reasonably well.

[15]:
sc.pl.embedding(adata, basis="X_mde", color=["cell_type"], frameon=False, ncols=1)
../../_images/tutorials_notebooks_harmonization_24_0.png

At a quick glance, it looks like the integration worked well. Indeed, the two datasets are relatively mixed in latent space and the cell types cluster together. We see that this dataset is quite complex, where only some batches contain certain cell types.

Compute integration metrics#

To quantify integration performance, we compute a subset of the metrics from scIB. Note that metrics are manipulated/scaled so that higher is always better, and these metrics might not represent the same exact value as when they were originally described (e.g., ilisi, clisi in this case).

[16]:
%%capture
def compute_scib_metrics(adata, emb_key, label_key, batch_key, model_name):
    from scib.metrics.silhouette import silhouette_batch, silhouette
    from scib.metrics.lisi import lisi_graph
    import pandas as pd

    emb_key_ = "X_emb"
    adata.obsm[emb_key_] = adata.obsm[emb_key]
    sc.pp.neighbors(adata, use_rep=emb_key_)
    df = pd.DataFrame(index=[model_name])
    df["ilisi"], df["clisi"] = lisi_graph(adata, batch_key, label_key, type_="embed")
    df["sil_batch"] = silhouette_batch(adata, batch_key, label_key, emb_key_)
    df["sil_labels"] = silhouette(adata, label_key, emb_key_)

    return df

emb_key = "X_scVI"
scvi_metrics = compute_scib_metrics(adata, emb_key, "cell_type", "batch", "scVI")
[17]:
scvi_metrics
[17]:
ilisi clisi sil_batch sil_labels
scVI 0.159869 0.985537 0.895221 0.534524

Integration with scANVI#

Previously, we used scVI as we assumed we did not have any cell type annotations available to guide us. Consequently, after the previous analysis, one would have to annotate clusters using differential expression, or by other means.

Now, we assume that all of our data is annotated. This can lead to a more accurate integration result when using scANVI, i.e., our latent data manifold is better suited to downstream tasks like visualization, trajectory inference, or nearest-neighbor-based tasks. scANVI requires:

  • the sample identifier for each cell (as in scVI)

  • the cell type/state for each cell

scANVI can also be used for label transfer and we recommend checking out the other scANVI tutorials to see explore this functionality.

Since we’ve already trained an scVI model on our data, we will use it to initialize scANVI. When initializing scANVI, we provide it the labels_key. As scANVI can also be used for datasets with partially-observed annotations, we need to give it the name of the category that corresponds to unlabeled cells. As we have no unlabeled cells, we can give it any random name that is not the name of an exisiting cell type.

Important

scANVI should be initialized from a scVI model pre-trained on the same exact data.

[18]:
lvae = scvi.model.SCANVI.from_scvi_model(
    vae,
    adata=adata,
    labels_key="cell_type",
    unlabeled_category="Unknown",
)
/usr/local/lib/python3.7/dist-packages/scvi/data/fields/_layer_field.py:79: UserWarning: adata.layers[counts] does not contain unnormalized count data. Are you sure this is what you want?
  f"{logger_data_loc} does not contain unnormalized count data. "
/usr/local/lib/python3.7/dist-packages/scvi/model/_scanvi.py:253: FutureWarning: elementwise comparison failed; returning scalar instead, but in the future will perform elementwise comparison
  labels == self.unlabeled_category_
/usr/local/lib/python3.7/dist-packages/scvi/model/_scanvi.py:255: FutureWarning: elementwise comparison failed; returning scalar instead, but in the future will perform elementwise comparison
  self._labeled_indices = np.argwhere(labels != self.unlabeled_category_).ravel()
[19]:
lvae.train(max_epochs=20, n_samples_per_label=100)
INFO     Training for 20 epochs.
GPU available: True, used: True
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]
Epoch 20/20: 100%|██████████| 20/20 [01:39<00:00,  4.96s/it, loss=628, v_num=1]

Now we can retrieve the latent space

[20]:
adata.obsm["X_scANVI"] = lvae.get_latent_representation(adata)

Again, we may visualize the latent space as well as the inferred labels

[21]:
adata.obsm["X_mde_scanvi"] = mde(adata.obsm["X_scANVI"])
[22]:
sc.pl.embedding(adata, basis="X_mde_scanvi", color=["cell_type"], ncols=1, frameon=False)
../../_images/tutorials_notebooks_harmonization_38_0.png

Compute integration metrics#

We can see that the additional training with label information and scANVI improved the metrics that capture bio conservation (clisi, sil_labels) without sacrificing too much batch correction power (ilisi, sil_batch)

[23]:
%%capture
emb_key = "X_scANVI"
scanvi_metrics = compute_scib_metrics(adata, emb_key, "cell_type", "batch", "scANVI")
[24]:
pd.concat([scvi_metrics, scanvi_metrics], axis=0)
[24]:
ilisi clisi sil_batch sil_labels
scVI 0.159869 0.985537 0.895221 0.534524
scANVI 0.144899 0.994963 0.880703 0.588642