Pandas数据操作分析基本常用的15个代码片段

import pandas as pd
 # Create a DataFrame
 data = {'Name': ['Alice', 'Bob', 'Charlie', 'David'],
         'Age': [25, 30, 35, 40]}
 df = pd.DataFrame(data)
 # Filter rows where Age is greater than 30
 filtered_df = df[df['Age'] > 30]
 print(filtered_df)

# Grouping by a column and calculating the mean
 grouped = df.groupby('Age').mean()
 print(grouped)

# Check for missing values
 missing_values = df.isnull().sum()
 # Fill missing values with a specific value
 df['Age'].fillna(0, inplace=True)

df['Age'] = df['Age'].apply(lambda x: x * 2)

# Concatenate two DataFrames
 df1 = pd.DataFrame({'A': ['A0', 'A1'], 'B': ['B0', 'B1']})
 df2 = pd.DataFrame({'A': ['A2', 'A3'], 'B': ['B2', 'B3']})
 result = pd.concat([df1, df2], ignore_index=True)
 print(result)

# Merge two DataFrames
 left = pd.DataFrame({'key': ['A', 'B', 'C'], 'value': [1, 2, 3]})
 right = pd.DataFrame({'key': ['B', 'C', 'D'], 'value': [4, 5, 6]})
 
 merged = pd.merge(left, right, on='key', how='inner')
 print(merged)

# Creating a pivot table
 pivot_table = df.pivot_table(index='Name', columns='Age', values='Value')
 print(pivot_table)

# Converting a column to DateTime
 df['Date'] = pd.to_datetime(df['Date'])

pandas.melt(frame, id_vars=None, value_vars=None, var_name=None, value_name='value', col_level=None)

ID  Name  Math  English  History
 0   1   Amy    90       85       88
 1   2   Bob    78       92       76
 2   3  John    88       79       90

melted_df=pd.melt(df, id_vars=['ID', 'Name'], value_vars=['Math', 'English', 'History'], var_name='Subject', value_name='Score')

ID  Name  Subject  Score
 0   1   Amy     Math     90
 1   2   Bob     Math     78
 2   3  John     Math     88
 3   1   Amy  English     85
 4   2   Bob  English     92
 5   3  John  English     79
 6   1   Amy  History     88
 7   2   Bob  History     76
 8   3  John  History     90

# Encoding categorical variables
 df['Category'] = df['Category'].astype('category')
 df['Category'] = df['Category'].cat.codes

# Randomly sample rows from a DataFrame
 sampled_df = df.sample(n=2)

# Calculating cumulative sum
 df['Cumulative_Sum'] = df['Values'].cumsum()

# Removing duplicate rows
 df.drop_duplicates(subset=['Column1', 'Column2'], keep='first', inplace=True)

# Creating dummy variables for categorical data
 dummy_df = pd.get_dummies(df, columns=['Category'])

# Exporting DataFrame to CSV
 df.to_csv('output.csv', index=False)