利用pandas处理Excel数据

import pandas as pd
import numpy as np

df = pd.read_excel('table1.xlsx') # 相对路径
# df = pd.read_excel(r'E:\Anaconda\hc\dataScience\table1.csv') # 绝对路径

df.shape

(6, 5)

df.dtypes

Name      object
Age        int64
Sex        int64
Class      int64
Score    float64
dtype: object

df.columns

Index(['Name', 'Age', 'Sex', 'Class', 'Score'], dtype='object')

df.head(2)

df.tail(3)

df['Score'].unique()

array([ 80.,  90., 100.,  nan])

# 没有读取第2行
df1 = pd.read_excel('table1.csv',skiprows=[2] ) 

# 所有缺失值显示为True
df.isnull()

df2 = df.dropna(how='any')

df3 = df.fillna(value=0)

df4 = df['Score'].fillna(df['Score'].mean())

0     80.0
1     90.0
2    100.0
3     90.0
4     88.0
5     80.0
Name: Score, dtype: float64

df1['Score'].astype('int64')

0     80
1     90
2    100
3     90
5     80
Name: Score, dtype: int64

df5 = df.rename(columns={'Score': 'score'})

df6 = df['Name'].replace('Bob', 'bob')

0     Tom
1    Jack
2    Alan
3    Tony
4     Tim
5     bob
Name: Name, dtype: object

df.sort_values(by=['Score'])

# 如果Score列的值>=85，Score列显示high，否则显示low
# group列为增加列
df['group'] = np.where(df['Score'] > 85,'high','low')

# 利用loc函数，进行多列查询
# sign为增加列
df.loc[(df['Sex'] == 1) & (df['Age']>= 19), 'sign']=1

df.loc[0:3]

df.iloc[:4, :5]

#[0, 2, 5] 代表指定的行，[0, 1, 5] 代表指定的列
df.iloc[[0, 2, 5],[0, 1, 5]]

# 判断Sex是否为1
df['Sex'].isin([1])

0     True
1     True
2     True
3    False
4    False
5     True
Name: Sex, dtype: bool

# Sex为1，分数大于85
df1.loc[(df1['Sex'] == 1) & (df1['Score'] > '85'), ['Name','Age','Class']]

# 先判断Score列里是否包含80和90，然后将复合条件的数据提取出来。
df.loc[df['Score'].isin(['80','90'])]