def runPrismX(clusterCount: int):
#urllib.request.urlretrieve("https://mssm-seq-matrix.s3.amazonaws.com/mouse_matrix.h5", "mouse_matrix.h5")
start = time.time()
correlationFolder = "correlation_" + str(clusterCount) + "_folder_q"
predictionFolder = "prediction_" + str(clusterCount) + "_folder_q"
libs = px.list_libraries()
gmt_file = px.load_library(libs[110])
px.createCorrelationMatrices("mouse_matrix.h5",
correlationFolder,
clusterCount=clusterCount,
sampleCount=5000,
correlationSampleCount=5000,
verbose=True)
t1 = time.time() - start
print("T1: " + str(t1))
px.correlation_scores(gmt_file,
correlationFolder,
predictionFolder,
verbose=True)
t2 = time.time() - start
print("T2: " + str(t2))
model = px.trainModel(predictionFolder,
correlationFolder,
gmt_file,
training_size=300000,
test_train_split=0.1,
sample_positive=40000,
sample_negative=200000,
random_state=42,
verbose=True)
pickle.dump(model, open("gobp_model_" + str(clusterCount) + ".pkl", 'wb'))
t3 = time.time() - start
print("T3: " + str(t3))
import urllib.request
import prismx as px
import pickle
from memory_profiler import memory_usage
import os
import time
import matplotlib.pyplot as plt
import pandas as pd
import feather
from prismx.utils import load_json, get_config, get_data_path, read_gmt
from prismx.loaddata import get_genes
from progress.bar import Bar
import numpy as np
px.print_libraries()
libs = px.list_libraries()
gmt_file = px.load_library(libs[28])
outname = libs[28]
correlationFolder = "correlation_100_folder"
predictionFolder = "prediction_100_folder"
outfolder = "prismxresult_100"
px.predict_gmt("gobp_model_100.pkl",
gmt_file,
correlationFolder,
predictionFolder,
outfolder,
outname,
step_size=1000,
verbose=True)