获取数据

链接:https://pan.baidu.com/s/1E8akk1gX9zppCViOQLDiUQ  密码:f66q

导入模块

import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib as mpl

import matplotlib.pyplot as plt
from IPython.display import display

plt.style.use('fivethirtyeight')
sns.set_style({'font.sans-serif':['simhei','Arial']})
%matplotlib inline

数据规整

lj_df = pd.read_csv('E:\\Test\\DataAnalysis\\lianjia\\lianjia.csv')
display(lj_df.head())

# 获取所有数据列信息
lj_df.info()

RangeIndex: 23677 entries, 0 to 23676
Data columns (total 12 columns):
Direction     23677 non-null object
District      23677 non-null object
Elevator      15440 non-null object
Floor         23677 non-null int64
Garden        23677 non-null object
Id            23677 non-null int64
Layout        23677 non-null object
Price         23677 non-null float64
Region        23677 non-null object
Renovation    23677 non-null object
Size          23677 non-null float64
Year          23677 non-null int64
dtypes: float64(2), int64(3), object(7)
memory usage: 2.2+ MB

df = lj_df.copy()
df

df['PerPrice'] = lj_df['Price']/lj_df['Size']
df

# 重新摆放列位置
columns = ['Region', 'District', 'Garden', 'Layout', 'Floor', 'Year', 'Size', 'Elevator', 'Direction', 'Renovation', 'PerPrice', 'Price']
df = pd.DataFrame(df, columns = columns)

# 重新审视数据集
display(df.head(n=2))

数据分析