Mercurial > repos > md-anderson-bioinformatics > matrix_manipulation

comparison Matrix_Statistics.py @ 1:f1bcd79cd923 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author insilico-bob
date Tue, 27 Nov 2018 14:20:40 -0500
parents
children
comparison
equal deleted inserted replaced
0:7f12c81e2083 1:f1bcd79cd923
1 '''
2 Created on Feb2018
3
4 @author: bob brown
5 '''
6
7 import sys, traceback, argparse
8 import numpy as np
9 from Matrix_Validate_import import reader
10 #import matplotlib.pyplot as plt
11 from Matrix_Filters import Variance_Percent_Filter_row, Variance_Percent_Filter_col
12
13 #Define argparse Function
14 def get_args():
15 parser = argparse.ArgumentParser()
16 parser.add_argument('input_file_txt', help='tab delimited text file input matrix(include .txt in name)')
17 parser.add_argument('choice',type=str, help='Variance Filter Method (Variance or Range)')
18 parser.add_argument('thresh', help='Thershold for Variance Filtering')
19 parser.add_argument('axes', help='Axes to Filter on (Either Row or Column')
20 parser.add_argument('output_file_txt', help='tab delimited text file output name (include .txt in name)')
21 args = parser.parse_args()
22 return args
23
24
25 #Define Function Which Labels Rows/Columns on Output
26 def labeler(matrix,filter_rows,filter_cols,output_file_txt):
27
28 #Write Data to Specified Text File Output
29 with open(output_file_txt,'w') as f:
30 f.write("")
31 for k in range(0,len(filter_cols)):
32 f.write('\t' + filter_cols[k])
33 f.write('\n')
34 for i in range(0,len(filter_rows)):
35 f.write(filter_rows[i])
36 for j in range(0,len(matrix[0])):
37 f.write('\t' + format(matrix[i][j]))
38 f.write('\n')
39
40
41 def Histo(matrix):
42 numBins= 20
43 data = []
44 # numRow,numCol= np.shape(matrix)
45 for i in range(len(matrix[0])):
46 data.append(np.nanmean([row[i] for row in matrix]))
47
48 # print(str(np.nanmean([row[i] for row in matrix])))
49
50 #https://stackoverflow.com/questions/5328556/histogram-matplotlib
51 #bins = [0, 40, 60, 75, 90, 110, 125, 140, 160, 200]
52 minBin = int(min(data)-0.5)
53 maxBin = int(max(data)+0.5)
54 binWidth = float(maxBin-minBin)/numBins
55 bins= []
56 """
57 for j in range(numBins):
58 bins.append(minBin+ j*binWidth)
59 #bins= 20
60 n, bins, patches = plt.hist(data,bins, normed=False)
61 #n, bins, patches = plt.hist(data,bins, normed=1, color='green')
62 #hist, bins = np.histogram(data, bins=bins)
63 width = np.diff(bins)
64 center = (minBin + bins[1:]) / 2
65
66 cm = plt.cm.get_cmap('RdYlBu_r')
67 #col = (n-n.min())/(n.max()-n.min())
68 for c, p in zip(bins, patches):
69 plt.setp( p, 'facecolor', cm(c/numBins))
70 fig, ax = plt.subplots(num=1, figsize=(8,3))
71 ax.set_title("Distribution of Column Means")
72 #ax.bar(center,bins, align='center', width=width)
73 #ax.bar(center, hist, align='center', width=width)
74 #ax.set_xticks(bins)
75 # fig.savefig("/Users/bobbrown/Desktop/Matrix-tools-Test-output/Column_Mean_Histogram.png")
76
77 plt.show()
78 """
79 return()
80
81 #========== test create variable number output files in Galaxy
82 def CreateFiles(output_file_info):
83
84 for i in range(3):
85 fd= open( output_file_info, 'w')
86 fd.write('File number = '+ str(i)+"\n")
87 fd.close()
88
89 return()
90
91 #==================
92
93 #Define Main Function
94 def main():
95 try:
96 args = get_args()
97 #sys.stdout.write(str(args)+"\n")
98 nanList= ["NAN", "NA", "N/A", "-","?","nan", "na", "n/a"]
99
100 matrix, og_cols,og_rows = reader(args.input_file_txt)
101 #old_reader matrix, og_rows, og_cols = reader(args.input_file_txt)
102 # if float(args.thresh) < 0.000001:
103 # print('Invalid negative threshold chosen = '+str(args.thresh)+" choose positive value")
104 # sys.exit(-4)
105
106 if args.choice == "Histogram":
107 Histo(matrix)
108 elif args.choice == "CreateFiles":
109 CreateFiles(args.output_file_info)
110
111 elif args.choice == "Variance":
112 if args.axes == "Row":
113 matrix, filter_rows, filter_cols,delCnt,minVal,maxVal = Variance_Percent_Filter_row(matrix,1,og_rows,og_cols,True)
114 labeler(matrix,filter_rows,filter_cols,args.output_file_txt)
115 # if delCnt < 1:
116 # print('\nNO Filtering occurred for rows using variance < '+str(args.thresh)+ ' by row. Matrix row minimum variance= %.2f' % minVal+' and maximum variance= %.2f' % maxVal)
117 # sys.stderr.write('\nFiltering out rows using variance < '+str(args.thresh)+ ' removed '+str(delCnt)+' rows')
118 # sys.exit(-1)
119 # else:
120 # print('\nFiltering out rows using variance < '+str(args.thresh)+ ' removed '+str(delCnt)+' rows')
121 elif args.axes == "Column":
122 matrix, filter_rows, filter_cols,delCnt,minVal,maxVal = Variance_Percent_Filter_col(matrix,1,og_rows,og_cols,True)
123 labeler(matrix,filter_rows,filter_cols,args.output_file_txt)
124 # if delCnt < 1:
125 # print('\nNO Filtering occurred for columns using variance < '+str(args.thresh)+ ' by columns. Matrix columns minimum variance= %.2f' % minVal+' and maximum variance= %.2f' % maxVal)
126 # sys.stderr.write('\nFiltering out rows using variance < '+str(args.thresh)+ ' removed '+str(delCnt)+' rows')
127 # sys.exit(-1)
128 # else:
129 # print('\nFiltering out columns using variance < '+str(args.thresh)+ ' removed '+str(delCnt)+' columns')
130 else:
131 print('Invalid Axes = '+str(args.axes))
132 sys.exit(-1)
133 else:
134 print("Invalid Filter Choice = "+str(args.choice))
135 sys.exit(-2)
136
137
138 except Exception as err:
139 traceback.print_exc()
140 sys.exit(-3)
141
142 if __name__ == '__main__':
143 main()
144 print("\nFini")
145 sys.exit(0)