In [6]:
import pandas as pd
git_log = pd.read_csv("../dataset/git_demo_timestamp_linux.gz")
git_log.head()
Out[6]:
In [7]:
top10 = git_log.author.value_counts().head(10)
top10
Out[7]:
In [12]:
%matplotlib inline
top10.plot.pie(title="TOP 10 committer", label="", figsize=[7,7])
Out[12]:
In [9]:
git_log.timestamp = pd.to_datetime(git_log.timestamp)
git_log.head()
Out[9]:
In [10]:
git_log.timestamp.dt.hour.value_counts(sort=False).plot.bar()
Out[10]: