
import os

os.environ["PYTHONHASHSEED"] = "0"


import scanpy as sc
import numpy as np
import random

sc.set_figure_params(figsize=(8, 8))

Matplotlib created a temporary config/cache directory at /tmp/matplotlib-6yr9h7rc because the default path (/home/sturm/.config/matplotlib) is not a writable directory; it is highly recommended to set the MPLCONFIGDIR environment variable to a writable directory, in particular to speed up the import of Matplotlib and to better support multiprocessing.


np.random.seed(0)  # Numpy random
random.seed(0)  # Python random


input_adata = "../data/adata_scvi.h5ad"


# Parameters
input_adata = "adata_scvi.h5ad"


sc.logging.print_versions()

WARNING: If you miss a compact list, please try `print_header`!

-----
anndata     0.7.6
scanpy      1.7.2
sinfo       0.3.1
-----
PIL                 8.3.2
anndata             0.7.6
backcall            0.2.0
beta_ufunc          NA
binom_ufunc         NA
cffi                1.14.6
colorama            0.4.4
concurrent          NA
cycler              0.10.0
cython_runtime      NA
dateutil            2.8.2
decorator           5.1.0
defusedxml          0.7.1
dunamai             1.6.0
encodings           NA
genericpath         NA
get_version         3.5.3
h5py                3.4.0
igraph              0.9.6
ipykernel           6.0.3
ipython_genutils    0.2.0
jedi                0.18.0
joblib              1.1.0
kiwisolver          1.3.2
legacy_api_wrap     0.0.0
leidenalg           0.8.7
llvmlite            0.37.0
matplotlib          3.4.3
matplotlib_inline   NA
mpl_toolkits        NA
natsort             7.1.1
nbinom_ufunc        NA
ntpath              NA
numba               0.54.1
numexpr             2.7.3
numpy               1.20.3
opcode              NA
packaging           21.0
pandas              1.3.3
parso               0.8.2
pexpect             4.8.0
pickleshare         0.7.5
pkg_resources       NA
posixpath           NA
prompt_toolkit      3.0.20
ptyprocess          0.7.0
pydoc_data          NA
pyexpat             NA
pygments            2.10.0
pyparsing           2.4.7
pytz                2021.3
scanpy              1.7.2
scipy               1.7.1
sinfo               0.3.1
six                 1.16.0
sklearn             1.0
sphinxcontrib       NA
sre_compile         NA
sre_constants       NA
sre_parse           NA
storemagic          NA
tables              3.6.1
texttable           1.6.4
tornado             6.1
traitlets           5.1.0
typing_extensions   NA
wcwidth             0.2.5
yaml                5.4.1
zmq                 22.3.0
-----
IPython             7.28.0
jupyter_client      6.1.12
jupyter_core        4.8.1
-----
Python 3.9.7 | packaged by conda-forge | (default, Sep 29 2021, 19:20:46) [GCC 9.4.0]
Linux-3.10.0-1160.11.1.el7.x86_64-x86_64-with-glibc2.28
44 logical CPU cores
-----
Session information updated at 2021-10-16 08:08


!lscpu

Architecture:        x86_64
CPU op-mode(s):      32-bit, 64-bit
Byte Order:          Little Endian
Address sizes:       46 bits physical, 48 bits virtual
CPU(s):              44
On-line CPU(s) list: 0-43
Thread(s) per core:  1
Core(s) per socket:  22
Socket(s):           2
NUMA node(s):        2
Vendor ID:           GenuineIntel
CPU family:          6
Model:               79
Model name:          Intel(R) Xeon(R) CPU E5-2699A v4 @ 2.40GHz
Stepping:            1
CPU MHz:             2400.000
CPU max MHz:         2400.0000
CPU min MHz:         1200.0000
BogoMIPS:            4794.35
Virtualization:      VT-x
L1d cache:           32K
L1i cache:           32K
L2 cache:            256K
L3 cache:            56320K
NUMA node0 CPU(s):   0-10,22-32
NUMA node1 CPU(s):   11-21,33-43
Flags:               fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch epb cat_l3 cdp_l3 invpcid_single intel_ppin intel_pt ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm rdt_a rdseed adx smap xsaveopt cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts md_clear spec_ctrl intel_stibp flush_l1d


adata = sc.read_h5ad(input_adata)


sc.pp.neighbors(adata, use_rep="X_scVI")
sc.tl.umap(adata)
sc.tl.leiden(adata)


(
    adata.obsp["connectivities"].sum(),
    adata.obsp["connectivities"][
        np.random.choice(adata.shape[0], 1000, replace=False), :
    ].sum(),
)

(170527.84, 6511.5127)


sc.pl.umap(adata, color="leiden", legend_loc="on data")


adata.obs["leiden"].value_counts()

0     4268
1     2132
2     1691
3     1662
4     1659
5     1563
6     1443
7     1210
8     1043
9     1022
10     952
11     837
12     809
13     804
14     733
15     703
16     570
17     506
18     503
19     438
20     433
21     346
22     273
23     182
24     144
25     141
26     137
27      82
28      76
29      57
30      55
31      40
Name: leiden, dtype: int64