Learn Data Analysis with Pandas

                                

# Function to double the value

def double(x):
  return 2 * x

# Apply this function to each value in a column

df['column1'] = df['column1'].apply(double)

# You can also use lambda functions for quick operations

df['column2'] = df['column2'].apply(lambda x: 3 * x)

# Apply a function across rows to create a new column

df['newColumn'] = df.apply(lambda row: row['column1'] * 1.5 + row['column2'], axis=1)


                              

                                

# Add a new column with specific values

df['newColumn'] = [1, 2, 3, 4]

# Set all values in a new column to the same value

df['newColumn'] = 1

# Create a new column by calculating from an existing column

df['newColumn'] = df['oldColumn'] * 5


                              

                                

# Create DataFrame from a dictionary

data = {'name': ['Anthony', 'Maria'], 'age': [30, 28]}
df = pd.DataFrame(data)

# Create DataFrame from a list of lists

data = [['Tom', 20], ['Jack', 30], ['Meera', 25]]
df = pd.DataFrame(data, columns=['Name', 'Age'])

# Create DataFrame by reading a CSV file

df = pd.read_csv('students.csv')


                              

                                

import pandas as pd


                              

                                

# Create a DataFrame

df = pd.DataFrame([
  ['Amy', 'Assignment 1', 75],
  ['Amy', 'Assignment 2', 35],
  ['Bob', 'Assignment 1', 99],
  ['Bob', 'Assignment 2', 35]
], columns=['Name', 'Assignment', 'Grade'])

# Group by 'Name' and calculate the average grade

df.groupby('Name')['Grade'].mean()

# Output:
# | Name | Grade |
# | ---  | ---   |
# | Amy  | 55    |
# | Bob  | 67    |


                              

                                

# Calculate different statistics for a column

df['columnName'].mean()    # Average

df['columnName'].std()     # Standard deviation

df['columnName'].median()  # Median

df['columnName'].max()     # Maximum value

df['columnName'].min()     # Minimum value

df['columnName'].count()   # Count of values

df['columnName'].nunique() # Number of unique values

df['columnName'].unique()  # List of unique values