15个高效的Pandas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)

 # Applying a custom function to a column
 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'])

 # Melting a DataFrame
 melted_df = pd.melt(df, id_vars=['Name'], value_vars=['A', 'B'])
 print(melted_df)

 # 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)

 dummy_df = pd.get_dummies(df, columns=['Category'])

 df.to_csv('output.csv', index=False)