pandas常用方法

import pandas as pd
# 读取CSV文件
df = pd.read_csv('data.csv')
# 读取Excel文件
df = pd.read_excel('data.xlsx')
# 读取SQL数据
import sqlite3
conn = sqlite3.connect('data.sqlite')
df = pd.read_sql_query('SELECT * FROM table', conn)
# 读取JSON数据
df = pd.read_json('data.json')

import pandas as pd
# 从列表创建DataFrame
data = {'name': ['Tom', 'Jerry', 'Mickey'], 'age': [25, 30, 35]}
df = pd.DataFrame(data)
# 从字典创建DataFrame
data = [['Tom', 25], ['Jerry', 30], ['Mickey', 35]]
df = pd.DataFrame(data, columns=['name', 'age'])
# 从CSV文件创建DataFrame
df = pd.read_csv('data.csv')

import pandas as pd
# 删除重复行
df.drop_duplicates(inplace=True)
# 删除缺失值
df.dropna(inplace=True)
# 填充缺失值
df.fillna(value=0, inplace=True)
# 替换值
df.replace('old_value', 'new_value', inplace=True)

import pandas as pd
# 按照某一列分组
grouped = df.groupby('column_name')
# 按照多列分组
grouped = df.groupby(['column_name1', 'column_name2'])
# 对分组后的数据进行聚合操作
grouped.agg({'column_name': 'sum'})

import pandas as pd
# 按照某一列合并
merged = pd.merge(df1, df2, on='column_name')
# 按照多列合并
merged = pd.merge(df1, df2, on=['column_name1', 'column_name2'])
# 连接两个DataFrame
merged = pd.concat([df1, df2], axis=0)

import pandas as pd
import matplotlib.pyplot as plt
# 绘制柱状图
df.plot(kind='bar')
# 绘制折线图
df.plot(kind='line')
# 绘制散点图
df.plot(kind='scatter', x='column_name1', y='column_name2')
# 绘制饼图
df['column_name'].value_counts().plot(kind='pie')

import pandas as pd
# 计算平均值
df['column_name'].mean()
# 计算中位数
df['column_name'].median()
# 计算标准差
df['column_name'].std()

import pandas as pd
# 导出CSV文件
df.to_csv('data.csv', index=False)
# 导出Excel文件
df.to_excel('data.xlsx', index=False)
# 导出SQL数据
import sqlite3
conn = sqlite3.connect('data.sqlite')
df.to_sql('table_name', conn, if_exists='replace', index=False)
# 导出JSON数据
df.to_json('data.json', orient='records')