rearrangefiles

#!/usr/bin/env python3
# -*- coding: latin-1 -*-
#
#   Copyright 2019-2025 Blaise Frederick
#
#   Licensed under the Apache License, Version 2.0 (the "License");
#   you may not use this file except in compliance with the License.
#   You may obtain a copy of the License at
#
#       http://www.apache.org/licenses/LICENSE-2.0
#
#   Unless required by applicable law or agreed to in writing, software
#   distributed under the License is distributed on an "AS IS" BASIS,
#   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
#   See the License for the specific language governing permissions and
#   limitations under the License.
#
#
import sys  # this goes up at the top where you are importing things

import numpy as np
import pandas as pd

if (
    len(sys.argv) != 2
):  # sys.argv[0] is always the name of the program, so the first command line argument is sys.argv[1].  Because arrays start at 0, that means the length is 2 if you have one argument.
    print("you should have one and only argument")
    sys.exit()

thefilenames = sys.argv[1]

# read the filenames in from the file with pandas, convert the 0th column to a python list
nameframe = pd.read_csv(thefilenames, header=None, engine="python")
thefiles = nameframe.ix[:, 0].tolist()

output_df = None
for thefilename in thefiles:
    df = pd.read_csv(thefilename, engine="python")

    columnlist = df.columns.values.tolist()[
        1:
    ]  # the index at the end cuts out the first column, which is the row names, not data
    rowlist = df["sources"].values.tolist()

    names = []
    values = []
    for row in range(len(rowlist)):
        for col in range(len(columnlist)):
            names.append(rowlist[row] + " " + columnlist[col])
            values.append(df[columnlist[col]][row])
    thedata = {thefilename: np.asarray(values, dtype=np.float64)}
    if output_df is None:
        print(thefilename, "is the first file - initializing output frame")
        output_df = pd.DataFrame(data=thedata, index=np.asarray(names, dtype=np.str))
    else:
        print(thefilename, "is a subsequent file - appending to output frame")
        temp_df = pd.DataFrame(data=thedata, index=np.asarray(names, dtype=np.str))
        output_df = pd.merge(output_df, temp_df, right_index=True, left_index=True)

print(output_df)
output_df.to_csv("allsubjects.csv")