# -*-coding:utf-8-*-

#  by kevinelstri
#  2017.2.16

# ---------------------
# Chapter 4: Find out on which weekday people bike the most with groupby and aggregate
# ---------------------

import pandas as pd
import matplotlib.pyplot as plt

"""
    4.1 Adding a 'weekday' column to our dataframe
"""
 

bikes = pd.read_csv('../data/bikes.csv', sep=';', encoding='latin1', index_col='Date', parse_dates=['Date'],
                    dayfirst=True)
print bikes.head()

bikes['Berri 1'].plot()  # 繪製曲線
# plt.show()

berri_bikes = bikes[['Berri 1']].copy()  # 將某一列的資料複製出來，單獨為一列
print berri_bikes[:5]
print berri_bikes.index
print
 
 berri_bikes.index.day
print berri_bikes.index.weekday
berri_bikes.loc[:, 'weekday'] = berri_bikes.index.weekday
print berri_bikes[:5]

"""
    4.2 Adding up the cyclists by weekday
"""
"""
    使用DataFrames中的.groupby()方法進行分組，並計算每一組的數量和
"""
weekday_counts = berri_bikes.groupby('weekday').aggregate(sum)
print
 
 weekday_counts

weekday_counts.index = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
print weekday_counts

weekday_counts.plot(kind='bar')
# plt.show()

"""
    4.3 Putting it together
"""
"""
    所有程式碼彙總
"""
bikes = pd.read_csv('../data/bikes.csv', sep=';', encoding='latin1', index_col='Date', dayfirst=True,
                    parse_dates=['Date'])
berri_bikes = bikes[['Berri 1']].copy()
berri_bikes.loc[:, 'weekday'] = berri_bikes.index.weekday

weekday_counts = berri_bikes.groupby('weekday').aggregate(sum)
weekday_counts.index = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
weekday_counts.plot(kind='bar')
plt.show()

"""
    分析：
        主要是計算時間，分組處理一週時間，將每週對應的數量加到對應的天上
    方法：
        1、csv資料的讀取
        2、列資料的複製
        3、將資料按照一週來進行劃分
        4、按照一週進行分組處理資料，修改索引
        5、直方圖展示
"""