In [1]:
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
%config InlineBackend.figure_format='retina'
In [2]:
df = pd.read_csv("austin_bikeshare_20191101.csv")
In [3]:
df['start_time'] = pd.to_datetime(df['start_time'])
df['start_date'] = df['start_time'].dt.date
df['start_hour'] = df['start_time'].dt.hour
In [4]:
date = '2019-11-05'
print(date)
In [5]:
filter_df = df[df['start_date'].astype(str) == date]
In [6]:
filter_df.head()
Out[6]:
In [7]:
filter_df.groupby(['start_hour'])[['trip_id']].count().plot();
In [8]:
filter_df.groupby(['subscriber_type'])[['trip_id']].count().plot.barh();
In [9]:
filter_df.groupby(['start_station_id'])['start_station_id'].count().plot.barh(figsize=(20, 10));
In [10]:
plt.figure(figsize=(12,8))
plt.title("start station id count per start hour")
sns.heatmap(filter_df.groupby(['start_hour', 'start_station_id'])[['start_station_id']].count().unstack(),
lw=.5, annot=True, cmap='GnBu', fmt='g', annot_kws={'size':10});
In [ ]: