dest="TSNE")
parser.add_argument("--tsne-na",
type=float,
default=-1e3,
help="numerical value to use for missing values",
dest="NA_VALUE")
parser.add_argument(
"--tsne-npca",
type=int,
help="number of principal components to take before t-SNE",
dest="N_PCA")
args = parser.parse_args()
# load input expression matrix
emx = dataframe_helper.load(args.INPUT)
print("Loaded %s %s" % (args.INPUT, str(emx.shape)))
# load label file or generate empty labels
if args.LABELS != None:
print("Loading label file...")
labels = np.loadtxt(args.LABELS, dtype=str)
else:
labels = np.zeros(len(emx.columns), dtype=str)
# plot sample distributions
if args.DENSITY != None:
print("Plotting sample distributions...")
import dataframe_helper
import numpy as np
import pandas as pd
import sys
if __name__ == "__main__":
# parse command-line arguments
if len(sys.argv) != 2:
print("usage: python stats.py [infile]")
sys.exit(-1)
INFILE = sys.argv[1]
# load input data
emx = dataframe_helper.load(INFILE)
emx = emx.values
# print global stats
print("shape: %s" % str(emx.shape))
print("global:")
print(" min: %12.6f" % (np.nanmin(emx)))
print(" avg: %12.6f" % (np.nanmean(emx)))
print(" max: %12.6f" % (np.nanmax(emx)))
# print column-wise stats
colmeans = np.nanmean(emx, axis=0)
print("column-wise mean:")
print(" min: %12.6f" % (np.nanmin(colmeans)))
print(" avg: %12.6f" % (np.nanmean(colmeans)))
import argparse
import dataframe_helper
import numpy as np
import pandas as pd
if __name__ == "__main__":
# parse command-line arguments
parser = argparse.ArgumentParser()
parser.add_argument("--true", required=True, help="true expression matrix", dest="EMX_TRUE")
parser.add_argument("--test", required=True, help="test expression matrix", dest="EMX_TEST")
args = parser.parse_args()
# load input dataframes
emx_true = dataframe_helper.load(args.EMX_TRUE)
emx_test = dataframe_helper.load(args.EMX_TEST)
print("Loaded %s %s" % (args.EMX_TRUE, str(emx_true.shape)))
print("Loaded %s %s" % (args.EMX_TEST, str(emx_test.shape)))
# extract data matrix from each dataframe
X_true = emx_true.values
X_test = emx_test.values
# print warnings for various mismatches
if emx_true.shape != emx_test.shape:
print("warning: shape does not match")
if (emx_true.index != emx_test.index).any():
print("warning: row names do not match")