Data Fields

• datetime - 每小时日期+时间戳
• season - 1 =春天，2 =夏天，3 =秋天，4 =冬天
• holiday - 这一天是否被视为假日
• workingday - 这一天既不是周末也不是假日
• weather -
  • 1: 晴，少云，部分多云，部分多云。
  • 2: 雾+云，雾+碎云，雾+少云，雾
  • 3: 小雪，小雨+雷雨+散云，小雨+散云
  • 4: 大雨+冰盘+雷雨+雾，雪+雾
• temp - 温度摄氏
• atemp - “感觉”摄氏温度
• humidity - 相对湿度
• windspeed - 风的速度
• casual - 发起非注册用户租金的数目
• registered - 发起注册用户租金的数目
• count - 租金总额（因变量）

import pylab
import calendar
import numpy as np
import pandas as pd
import seaborn as sn
from scipy import stats
import missingno as msno
from datetime import datetime
import matplotlib.pyplot as plt
import warnings
pd.options.mode.chained_assignment = None
warnings.filterwarnings("ignore", category=DeprecationWarning)
%matplotlib inline
dailyData = pd.read_csv("train.csv")

Data Summary

作为第一步，我们可以在DataSet上做三个简单的步骤

• 数据集的大小
• 通过打印几行数据来了解数据。
• 什么类型的变量在我们的数据中？

dailyData.shape

输出 ： (10886, 12)

dailyData.head(2)

dailyData.dtypes

输出 ：
datetime object
season int64
holiday int64
workingday int64
weather int64
temp float64
atemp float64
humidity int64
windspeed float64
casual int64
registered int64
count int64
dtype: object

• Create new columns "date,"hour","weekDay","month" from "datetime" column.
• Coerce the datatype of "season","holiday","workingday" and weather to category.
• Drop the datetime column as we already extracted useful features from it.

dailyData["date"] = dailyData.datetime.apply(lambda x : x.split()[0])
dailyData["hour"] = dailyData.datetime.apply(lambda x : x.split()[1].split(":")[0])
dailyData["weekday"] = dailyData.date.apply(lambda dateString : calendar.day_name[datetime.strptime(dateString,"%Y-%m-%d").weekday()])
dailyData["month"] = dailyData.date.apply(lambda dateString : calendar.month_name[datetime.strptime(dateString,"%Y-%m-%d").month])
dailyData["season"] = dailyData.season.map({1: "Spring", 2 : "Summer", 3 : "Fall", 4 :"Winter" })
dailyData["weather"] = dailyData.weather.map({1: " Clear + Few clouds + Partly cloudy + Partly cloudy",\
                                        2 : " Mist + Cloudy, Mist + Broken clouds, Mist + Few clouds, Mist ", \
                                        3 : " Light Snow, Light Rain + Thunderstorm + Scattered clouds, Light Rain + Scattered clouds", \
                                        4 :" Heavy Rain + Ice Pallets + Thunderstorm + Mist, Snow + Fog " })



categoryVariableList = ["hour","weekday","month","season","weather","holiday","workingday"]
for var in categoryVariableList:
    dailyData[var] = dailyData[var].astype("category")


dailyData  = dailyData.drop(["datetime"],axis=1)


dataTypeDf = pd.DataFrame(dailyData.dtypes.value_counts()).reset_index().rename(columns={"index":"variableType",0:"count"})
fig,ax = plt.subplots()
fig.set_size_inches(12,5)
sn.barplot(data=dataTypeDf,x="variableType",y="count",ax=ax)
ax.set(xlabel='variableTypeariable Type', ylabel='Count',title="Variables DataType Count")

Missing Values Analysis

msno.matrix(dailyData,figsize=(12,5))http://localhost:8888/notebooks/pycon-2017-eda-tutorial-master/notebooks/ofo/Untitled.ipynb?kernel_name=python3#Missing-Values-Analysis

Outliers Analysis

fig, axes = plt.subplots(nrows=2,ncols=2)
fig.set_size_inches(12, 10)
sn.boxplot(data=dailyData,y="count",orient="v",ax=axes[0][0])
sn.boxplot(data=dailyData,y="count",x="season",orient="v",ax=axes[0][1])
sn.boxplot(data=dailyData,y="count",x="hour",orient="v",ax=axes[1][0])
sn.boxplot(data=dailyData,y="count",x="workingday",orient="v",ax=axes[1][1])

axes[0][0].set(ylabel='Count',title="Box Plot On Count")
axes[0][1].set(xlabel='Season', ylabel='Count',title="Box Plot On Count Across Season")
axes[1][0].set(xlabel='Hour Of The Day', ylabel='Count',title="Box Plot On Count Across Hour Of The Day")
axes[1][1].set(xlabel='Working Day', ylabel='Count',title="Box Plot On Count Across Working Day")

dailyDataWithoutOutliers = dailyData[np.abs(dailyData["count"]-dailyData["count"].mean())<=(3*dailyData["count"].std())] 
print ("Shape Of The Before Ouliers: ",dailyData.shape)
print ("Shape Of The After Ouliers: ",dailyDataWithoutOutliers.shape)

输出 ：
Shape Of The Before Ouliers: (10886, 15)
Shape Of The After Ouliers: (10739, 15)

corrMatt = dailyData[["temp","atemp","casual","registered","humidity","windspeed","count"]].corr()
mask = np.array(corrMatt)
mask[np.tril_indices_from(mask)] = False
fig,ax= plt.subplots()
fig.set_size_inches(20,10)
sn.heatmap(corrMatt, mask=mask,vmax=.8, square=True,annot=True)

fig,(ax1,ax2,ax3) = plt.subplots(ncols=3)
fig.set_size_inches(12, 5)
sn.regplot(x="temp", y="count", data=dailyData,ax=ax1)
sn.regplot(x="windspeed", y="count", data=dailyData,ax=ax2)
sn.regplot(x="humidity", y="count", data=dailyData,ax=ax3)

fig,(ax1,ax2,ax3,ax4)= plt.subplots(nrows=4)
fig.set_size_inches(12,20)
sortOrder = ["January","February","March","April","May","June","July","August","September","October","November","December"]
hueOrder = ["Sunday","Monday","Tuesday","Wednesday","Thursday","Friday","Saturday"]

monthAggregated = pd.DataFrame(dailyData.groupby("month")["count"].mean()).reset_index()
monthSorted = monthAggregated.sort_values(by="count",ascending=False)
sn.barplot(data=monthSorted,x="month",y="count",ax=ax1,order=sortOrder)
ax1.set(xlabel='Month', ylabel='Avearage Count',title="Average Count By Month")

hourAggregated = pd.DataFrame(dailyData.groupby(["hour","season"],sort=True)["count"].mean()).reset_index()
sn.pointplot(x=hourAggregated["hour"], y=hourAggregated["count"],hue=hourAggregated["season"], data=hourAggregated, join=True,ax=ax2)
ax2.set(xlabel='Hour Of The Day', ylabel='Users Count',title="Average Users Count By Hour Of The Day Across Season",label='big')

hourAggregated = pd.DataFrame(dailyData.groupby(["hour","weekday"],sort=True)["count"].mean()).reset_index()
sn.pointplot(x=hourAggregated["hour"], y=hourAggregated["count"],hue=hourAggregated["weekday"],hue_order=hueOrder, data=hourAggregated, join=True,ax=ax3)
ax3.set(xlabel='Hour Of The Day', ylabel='Users Count',title="Average Users Count By Hour Of The Day Across Weekdays",label='big')

hourTransformed = pd.melt(dailyData[["hour","casual","registered"]], id_vars=['hour'], value_vars=['casual', 'registered'])
hourAggregated = pd.DataFrame(hourTransformed.groupby(["hour","variable"],sort=True)["value"].mean()).reset_index()
sn.pointplot(x=hourAggregated["hour"], y=hourAggregated["value"],hue=hourAggregated["variable"],hue_order=["casual","registered"], data=hourAggregated, join=True,ax=ax4)
ax4.set(xlabel='Hour Of The Day', ylabel='Users Count',title="Average Users Count By Hour Of The Day Across User Type",label='big')