Python大数据分析，简单举例

数据来源百度网盘，提取码：lnqc 

二手房数据分析——文件名：lianjia.csv
 

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']})

# 导入链家二手房数据
lianjia_df = pd.read_csv('lianjia.csv')
display(lianjia_df.head(n=3))
lianjia_df.info()
lianjia_df.describe()

#添加新特征房屋均价
df = lianjia_df.copy()
df['PerPrice'] = lianjia_df['Price']/lianjia_df['Size']

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