-
Notifications
You must be signed in to change notification settings - Fork 1
/
stat_test.py
160 lines (116 loc) · 4.91 KB
/
stat_test.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
import matplotlib
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from scipy import stats
def perform_t_test(samples1, samples2):
[t_val, p_val] = stats.ttest_ind(samples1, samples2, equal_var=True)
print("t-Statistic value : {}".format(t_val))
print("p - value : {}".format(p_val))
print("=====================================")
def plot_normal_distributions(samples1, samples2):
fit1 = stats.norm.pdf(samples1, np.mean(samples1), np.std(samples1))
fit2 = stats.norm.cdf(samples2, np.mean(samples2), np.std(samples2))
plt.plot(sorted(samples1), fit1, 'red')
plt.plot(sorted(samples2), fit2, 'blue')
plt.show()
def get_box_plots(samples1, samples2, save_folder, title=None, file_name=None):
all_data = [samples1, samples2]
labels = ['Fake', 'Real']
# plt.box(None)
font = {'family': 'normal',
'weight': 'semibold',
'size': 13}
#
matplotlib.rc('font', **font)
# plt.xlabel('l', fontsize=18)
# plt.ylabel('ylabel', fontsize=16)
plt.tight_layout()
plt.figure(figsize=(1.5, 4))
fig = plt.figure(1, figsize=(1, 3), frameon=False)
ax1 = fig.add_subplot(111)
bplot1 = ax1.boxplot(all_data,
vert=True, # vertical box alignment
patch_artist=True, # fill with color
labels=labels, # will be used to label x-ticks
showfliers=False,
positions=[0, 0.5])
# plt.title(title)
# title = ax1.set_title("\n".join(wrap(title,50)), fontdict={'fontweight': 'semibold'})
[t_val, p_val] = stats.ttest_ind(samples1, samples2, equal_var=True)
if p_val > 0.05:
title = ax1.set_title(file_name, fontdict={'fontweight': 'bold', 'fontsize': 16})
else:
ax1.set_title(r'' + file_name + ' $\mathbf{^{*}}$', fontdict={'fontweight': 'bold', 'fontsize': 16})
# fill with colors
colors = ['pink', 'lightblue', 'lightgreen']
for patch, color in zip(bplot1['boxes'], colors):
patch.set_facecolor(color)
fig.savefig('{}/{}.png'.format(save_folder, file_name))
fig.show()
plt.close()
def get_box_plots_mod(samples1, samples2, save_folder, file_name=None):
all_data = np.transpose(np.array([samples1, samples2]))
labels = ['Fake', 'Real']
df = pd.DataFrame(all_data, columns=labels)
import seaborn as sns
import matplotlib.pyplot as plt
from matplotlib import pyplot
fig, ax = pyplot.subplots(figsize=(3, 3.5))
my_pal = {"Fake": "pink", "Real": "lightblue", }
plt.xticks(fontsize=12)
plt.yticks(fontsize=12)
ax = sns.boxplot(data=df, width=0.3, palette=my_pal, showfliers=False)
colors = ['pink', 'lightblue']
for idx, patch in enumerate(ax.artists):
r, g, b, a = patch.get_facecolor()
patch.set_facecolor(colors[idx])
[t_val, p_val] = stats.ttest_ind(samples1, samples2, equal_var=True)
if p_val > 0.05:
title = plt.title(file_name, fontdict={'fontweight': 'bold', 'fontsize': 16})
else:
plt.title(r'' + file_name + ' $\mathbf{^{*}}$', fontdict={'fontweight': 'bold', 'fontsize': 16})
plt.savefig('{}/{}.png'.format(save_folder, file_name),bbox_inches="tight")
plt.show()
return
font = {'family': 'normal',
'weight': 'semibold',
'size': 13}
#
matplotlib.rc('font', **font)
# plt.xlabel('l', fontsize=18)
# plt.ylabel('ylabel', fontsize=16)
plt.tight_layout()
plt.figure(figsize=(1.5, 4))
fig = plt.figure(1, figsize=(1, 3), frameon=False)
ax1 = fig.add_subplot(111)
# rectangular box plot
bplot1 = ax1.boxplot(all_data,
vert=True, # vertical box alignment
patch_artist=True, # fill with color
labels=labels, # will be used to label x-ticks
showfliers=False,
positions=[0, 0.5])
[t_val, p_val] = stats.ttest_ind(samples1, samples2, equal_var=True)
if p_val > 0.05:
title = ax1.set_title(file_name, fontdict={'fontweight': 'bold', 'fontsize': 16})
else:
ax1.set_title(r'' + file_name + ' $\mathbf{^{*}}$', fontdict={'fontweight': 'bold', 'fontsize': 16})
# fill with colors
colors = ['pink', 'lightblue', 'lightgreen']
for patch, color in zip(bplot1['boxes'], colors):
patch.set_facecolor(color)
fig.savefig('{}/{}.png'.format(save_folder, file_name))
fig.show()
plt.close()
if __name__ == "__main__":
import seaborn as sns
all_data = np.transpose(np.array([np.random.rand(2000, ), np.random.rand(2000, )]))
labels = ['Fake', 'Real']
df = pd.DataFrame(all_data, columns=labels)
my_pal = {"Fake": "pink", "Real": "lightblue", }
plt.xticks(fontsize=12)
plt.yticks(fontsize=12)
tips = sns.load_dataset("tips")
ax = sns.violinplot(data=df, palette=my_pal, width=0.3, showfliers=False)
plt.show()