-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathanalyzer.py
163 lines (122 loc) · 5.51 KB
/
analyzer.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
161
162
163
import pandas as pd
from sentiment_analysis import SentimentAnalysis
import matplotlib.pyplot as plt; plt.rcdefaults()
import numpy as np
import matplotlib.pyplot as plt
import extractor as const
class Analyzer:
datafile = 'dataframe.csv'
df = None
def __init__(self):
self.df = pd.read_csv(self.datafile, index_col=False)
def add_to_dataframe(self, ex, meta_data):
#sa = SentimentAnalysis(ex)
#sen = sa.getAvgSentiment()
new_row = {
'project': ex.repo_name,
'lang': ex.lang,
'lines': ex.get_line_count(),
'lo-code': ex.get_code_lines_count(),
'lo-comment': ex.get_comment_lines_count(),
'number-comments': ex.get_number_comments(),
'todo': ex.get_number_comment('todo'),
'todo-lines': ex.get_comment_line_count('todo'),
'class': ex.get_number_comment('class'),
'class-lines': ex.get_comment_line_count('class'),
'method': ex.get_number_comment('method'),
'method-lines': ex.get_comment_line_count('method'),
'header': ex.get_number_comment('header'),
'header-lines': ex.get_comment_line_count('header'),
'other': ex.get_number_comment('other'),
'other-lines': ex.get_comment_line_count('other'),
'avg-len': ex.get_avg_comment_len(),
'stars': meta_data['stargazers_count'],
'forks': meta_data['forks_count'],
'size': meta_data['size'],
'subscribers': meta_data['subscribers_count']
}
self.df = self.df.append(new_row, ignore_index=True)
self.df.to_csv(self.datafile, index=False)
def print_dataframe(self):
self.df.sort_values(by=['lang'], inplace=True)
print(self.df)
def plotCommentCodeBarChart(self, comments, title):
cpc = pd.DataFrame({'cpc': (comments / self.df['lo-code']).tolist()}, index=self.df['project'])
cpc = cpc.sort_values(by='cpc', ascending=False)
pl = cpc.plot.bar(rot=0, title=title)
pl.set_xlabel('projects')
plt.show()
def plotStarBarChart(self):
cpc = pd.DataFrame({'stars': (self.df['stars']).tolist(), 'forks': (self.df['forks']).tolist()}, index=self.df['project'])
cpc = cpc.sort_values(by='stars', ascending=False)
pl = cpc.plot.bar(rot=0, title='Stars/Forks on GitHub')
pl.set_xlabel('projects')
plt.show()
def plotSentimentBarChart(self):
sen = self.df.sort_values(by='com', ascending=False)
pl = sen.plot.bar(y='com',x='project', rot=0, title='Sentiment Analysis')
pl.set_ylabel('sentiment compound')
pl.set_xlabel('projects')
plt.show()
def plotCommentDistribution(self, lang):
comment_df = self.df[self.df.lang == lang][const.categories].sum()
pl = comment_df.plot.pie()
plt.show()
def plotOverviewBarChart(self, col, titel, yaxis):
comment_java = self.df[self.df.lang == 'java'][col].sum() / len(self.df[self.df.lang == 'java'])
comment_py = self.df[self.df.lang == 'py'][col].sum() / len(self.df[self.df.lang == 'py'])
objects = ('Java', 'Python')
y_pos = np.arange(len(objects))
plt.bar(y_pos, [comment_java, comment_py], align='center', alpha=0.5)
plt.xticks(y_pos, objects)
plt.ylabel(yaxis)
plt.title(titel)
plt.show()
def plotAvgCommentCode(self):
comment_java = (self.df[self.df.lang == 'java']['lo-comment'] / self.df['lo-code']).median()
comment_py = (self.df[self.df.lang == 'py']['lo-comment'] / self.df['lo-code']).median()
print(comment_java)
objects = ('Java', 'Python')
y_pos = np.arange(len(objects))
plt.bar(y_pos, [comment_java, comment_py], align='center', alpha=0.5)
plt.xticks(y_pos, objects)
plt.title('Average comment/code ratio')
plt.show()
def plotOverviewStackedBarChart(self):
t = self.df.groupby(['lang'])[const.categories].sum()
t.plot(kind='bar', stacked=True)
plt.show()
def plotCommentStarScatter(self):
y = self.df['lo-comment'] / self.df['lo-code']
x = self.df['stars']
plt.scatter(x, y)
plt.show()
def plotBoxplot(self, df, col, outliers=True):
#print('median', col, ':', df.median())
df.boxplot(col, showfliers=outliers)
plt.show()
def main():
analyzer = Analyzer()
df = analyzer.df
df_java = df[df.lang == 'java']
df_python = df[df.lang == 'py']
sum_java = df[df.lang == 'java']['lines'].sum()
print('sum lines java:', sum_java)
print('number java projects', len(df_java), '\n')
sum_py = df[df.lang == 'py']['lines'].sum()
print('sum lines pyhton:', sum_py)
print('number of python projects', len(df_python), '\n')
ratio_java = pd.DataFrame({'comment/code': df_java['lo-comment'] / df_java['lo-code']})
analyzer.plotBoxplot(ratio_java, 'comment/code')
ratio_py = pd.DataFrame({'comment/code': df_python['lo-comment'] / df_python['lo-code']})
analyzer.plotBoxplot(ratio_py, 'comment/code')
analyzer.plotBoxplot(df_java, 'avg-len')
analyzer.plotBoxplot(df_python, 'avg-len')
analyzer.plotAvgCommentCode()
analyzer.plotCommentDistribution('java')
analyzer.plotCommentDistribution('py')
analyzer.plotOverviewStackedBarChart()
analyzer.plotOverviewBarChart('avg-len', 'Average length of comment', 'length')
analyzer.plotCommentStarScatter()
if __name__ == "__main__":
main()