Welcome to PyJanitor

import pandas as pd
import janitor as jn

# Create a sample dataframe
df = pd.DataFrame({
    'a': [1, 2, 3],
    'b': [4, 5, 6],
    'Column with spaces': [7, 8, 9]
})

# Use method chaining to clean and transform data
clean_df = (
    df
    .clean_names()                # Convert column names to snake_case
    .rename_column('a', 'x')      # Rename a column
    .add_column('z', df['a'] * 2) # Add a new column
    .drop_columns('b')            # Remove a column
)

print(clean_df)

import pandas as pd
import janitor as jn

# DataFrame with problematic column names
df = pd.DataFrame({
    'First Name': ['John', 'Jane', 'Mike'],
    'Last-Name': ['Smith', 'Doe', 'Johnson'],
    'email@address': ['john@example.com', 'jane@example.com', 'mike@example.com'],
    '% complete': [85, 93, 75]
})

# Clean the column names
cleaned_df = df.clean_names()
print(cleaned_df.columns)
# Output: Index(['first_name', 'last_name', 'email_address', 'percent_complete'], dtype='object')

import numpy as np
import pandas as pd
import janitor as jn

# DataFrame with missing values
df = pd.DataFrame({
    'name': ['John', 'Jane', None, 'Mike'],
    'age': [30, np.nan, 25, 40],
    'score': [85, 92, None, 78]
})

# Handle missing values with method chaining
cleaned_df = (
    df
    .remove_empty()          # Remove completely empty rows
    .dropna(subset=['name']) # Remove rows with missing names
    .fillna(value={'age': df['age'].mean(), 'score': 0})
)

print(cleaned_df)