pandas常用数据分析语法(一):数据导入
1.概述
导入
import pandas as pd
import numpy as np
data_file = 'Arrest_Data_from_2010_to_2019.csv'
df = pd.read_csv(data_file)
df.head()
数据大小
len(df_2018)
列的描述
df['Arrest Date'].describe()
2.去掉空值
#计算Dataframe中空值的个数
df_2018['Charge Group Description'].isnull().sum()
df_4=df_4.dropna(subset = ['Charge Group Description']);
3.建立矩阵
#复制
df_4 = df_2018.copy()
#新建
tempRatio = pd.DataFrame(columns=['Charge Group Code', 'Area ID', 'Ratio'])
#拼接
dfRatio = pd.concat([dfRatio,tempRatio], ignore_index=True)
series
yearData['year']= op.index
yearData['counts']= op.values