pd.read_csv('file.csv') | Read a CSV file into a DataFrame |
df.to_csv('file.csv') | Write a DataFrame to a CSV file |
pd.read_excel('file.xlsx') | Read an Excel file into a DataFrame |
df.to_excel('file.xlsx') | Write a DataFrame to an Excel file |
df.head() | Get the first 5 rows of a DataFrame |
df.tail() | Get the last 5 rows of a DataFrame |
df.info() | Get information about a DataFrame, including data types and memory usage |
df.describe() | Get summary statistics of numerical columns in a DataFrame |
df[col] | Get a single column by name as a Series |
df[[col1, col2]] | Get multiple columns by name as a DataFrame |
df.loc[row, col] | Get a single value by row and column label |
df.iloc[row, col] | Get a single value by row and column index |
df['new_col'] = value | Add a new column to a DataFrame (or change existing value) |
df.drop(col, axis=1, inplace=True) | Remove/drop a column from a DataFrame |
df.drop(row, axis=0, inplace=True) | Remove/drop a row from a DataFrame |
df.sort_values(by=col, ascending=True) | Sort a DataFrame by a column |
df.groupby(col).sum() | Group a DataFrame by a column and compute the sum of each group |
df.groupby(col).median() | Group a DataFrame by a column and compute the median of each group |
df.groupby(col).max() | Group a DataFrame by a column and compute the maximum of each group |
df.groupby(col).first() | Group a DataFrame by a column and return the first row of each group |
df.groupby(col).size() | Group a DataFrame by a column and return the size of each group |
df.groupby(col).agg(func) | Group a DataFrame by a column and apply a specific aggregation function to each group |
Design based on Dracula UI