Pandas
Pandas 工具包使用
import pandas as pd
path = "data.csv"
df = pd.read_csv(path)
df.head()
print(help(pd.read_csv))
数据信息读取与展示
df = pd.read_csv("data.csv")
df.info()
df.index
df.columns
df.dtypes
df.values
data = {
'country' : ['aaa','bbb', 'ccc','ddd'],
'population': [10,12,14, np.nan]}
df_data = pd.DataFrame(data)
df_data
age = df['age']
age.values
age = age+10
age.mean()
age.max()
df.set_index('Name')
df.describe()
索引方法
df.iloc[0]
df.loc['Tom Hanks','Fare']
df[df['Fare']>40]
df[df['sex']=='Male']
df.loc[df['sex']=='Male','Age'].mean()
(df['Age'>70]).sum()
⚠️ Groupby 函数的使用方法
df = pd.DataFrame({
'key':['A', 'B', 'C', 'A', 'B', 'C','A'