rjawor/concordia-library
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

corpus figures creator

Browse Source
This commit is contained in:
rjawor 2015-10-06 13:34:03 +02:00
parent 96c74c47ac
commit f585ff9e01
1 changed files with 16 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
tools/prepare_corpus_figures.py
View File

@ -4,6 +4,7 @@
from os import listdir from os import listdir
import numpy as np import numpy as np
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
import sys
input_dir = 'stats' input_dir = 'stats'
@ -37,9 +38,9 @@ with open(output_dir+'/stats_table.tex', 'w') as stats_table:
stats_table.write(r'Corpus name & Total sentences & Non-empty & Unique\\'+'\n') stats_table.write(r'Corpus name & Total sentences & Non-empty & Unique\\'+'\n')
stats_table.write(r'\hline\hline'+'\n') stats_table.write(r'\hline\hline'+'\n')
for corpus in corpora: for corpus in corpora:
non_empty_percentage = float(100*corpus["total"] - corpus["empty"])/corpus["total"] non_empty_percentage = float(100*(corpus["total"] - corpus["empty"]))/corpus["total"]
unique_percentage = float(100*corpus["unique"])/corpus["total"] unique_percentage = float(100*corpus["unique"])/corpus["total"]
stats_table.write("%s & %d & %d (%.2f%%) & %d (%.2f%%) \\\\\n" % (corpus["name"], corpus["total"], corpus["total"] - corpus["empty"], non_empty_percentage, corpus["unique"], unique_percentage)) stats_table.write("%s & %d & %d (%.2f\%%) & %d (%.2f\%%) \\\\\n" % (corpus["name"], corpus["total"], corpus["total"] - corpus["empty"], non_empty_percentage, corpus["unique"], unique_percentage))
stats_table.write(r'\hline'+'\n') stats_table.write(r'\hline'+'\n')
stats_table.write(r'\end{tabular}'+'\n') stats_table.write(r'\end{tabular}'+'\n')
@ -59,7 +60,7 @@ for corpus in corpora:
freq_table.write(r'Occurences & Sentence\\'+'\n') freq_table.write(r'Occurences & Sentence\\'+'\n')
freq_table.write(r'\hline\hline'+'\n') freq_table.write(r'\hline\hline'+'\n')
for data in corpus["most_frequent"]: for data in corpus["most_frequent"]:
freq_table.write("%d & %s\n" % data) freq_table.write("%d & %s\\\\\n" % data)
freq_table.write(r'\hline'+'\n') freq_table.write(r'\hline'+'\n')
freq_table.write(r'\end{tabular}'+'\n') freq_table.write(r'\end{tabular}'+'\n')
freq_table.write(r'\caption{Most frequent sentences in the corpus '+corpus["name"]+'}\n') freq_table.write(r'\caption{Most frequent sentences in the corpus '+corpus["name"]+'}\n')
@ -69,23 +70,21 @@ for corpus in corpora:
# plot # plot
N = 5 N = len(corpora)
menMeans = (20, 35, 30, 35, 27) uniques = [float(100*corpus["unique"]) / corpus["total"] for corpus in corpora]
womenMeans = (25, 32, 34, 20, 25) repeated = [float(100*(corpus["total"] - corpus["unique"] - corpus["empty"])) / corpus["total"] for corpus in corpora]
menStd = (2, 3, 4, 1, 2) empty = [float(100*corpus["empty"]) / corpus["total"] for corpus in corpora]
womenStd = (3, 5, 2, 3, 3)
ind = np.arange(N) # the x locations for the groups ind = np.arange(N) # the x locations for the groups
width = 0.35 # the width of the bars: can also be len(x) sequence width = 0.35 # the width of the bars: can also be len(x) sequence
p1 = plt.bar(ind, menMeans, width, color='r', yerr=womenStd) p1 = plt.bar(ind, uniques, width, color='#009900')
p2 = plt.bar(ind, womenMeans, width, color='y', p2 = plt.bar(ind, repeated, width, color='#99FF66', bottom=uniques)
bottom=menMeans, yerr=menStd) p3 = plt.bar(ind, empty, width, color='#999966', bottom=[sum(x) for x in zip(repeated,uniques)])
plt.ylabel('Scores') plt.xticks(ind+width/2., [corpus["name"] for corpus in corpora] )
plt.title('Scores by group and gender') plt.yticks(np.arange(0,101,10))
plt.xticks(ind+width/2., ('G1', 'G2', 'G3', 'G4', 'G5') ) plt.legend( (p1[0], p2[0], p3[0]), ('unique', 'repeated', 'empty') )
plt.yticks(np.arange(0,81,10))
plt.legend( (p1[0], p2[0]), ('Men', 'Women') )
plt.savefig('bar_graph.eps', format='eps') plt.savefig(output_dir+'/bar_graph.eps', format='eps')