GRADE XII IP - DATAFRAME OPERATIONS | 9-4-26

 

PYTHON PANDAS BASIC DATAFRAME OPERATIONS

import pandas as pd

import numpy as np

print("\nPYTHON PANDAS BASIC DATAFRAME OPERATIONS")

# Creating DataFrame

data = {

    'Name': ['Amba', 'Radha', 'Sharada', 'Ayan'],

    'Score': [90, 76, 88, 89]

}

df = pd.DataFrame(data)

print("\nINITIAL DATAFRAME IS:\n")

print(df)

# Basic Operations

print("\nMaximum Value in the Entire DataFrame is:", df.values.max())

print("\nMinimum Value in Score Column is:", df['Score'].min())

print("\nMaximum Value in Score Column is:", df['Score'].max())

print("\nMean of Score Column is:", df['Score'].mean())

print("\nNumber of Records in DataFrame:\n", df.count())

print("\nSum of Score Column:", df['Score'].sum())

# Sorting

print("\nSorting DataFrame by Name:\n", df.sort_values('Name'))

# Updating using loc

print("\nUpdating Score of Second Row using loc")

df.loc[1, 'Score'] = 85

print(df)

# Accessing specific row

print("\nPrinting Fourth Row:\n", df.loc[3, ['Name', 'Score']])

# Adding new column

print("\nAdding New Column 'Position'")

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

print(df)

# Fill NaN values

print("\nUsing fillna to Replace NaN with 0")

df = df.fillna(0)

print(df)

# Where condition

print("\nRows where Score > 88:\n", df.where(df['Score'] > 88))

# Replace values using where

print("\nReplacing 90 with 92 in Score column")

df['Score'] = df['Score'].where(df['Score'] != 90, 92)

print(df)

# Deleting row

print("\nDeleting Row with Index 1")

df = df.drop(1)

print(df)

# DataFrame from Nested List

print("\nCreating DataFrame from Nested List")

lst = [['S1', 'Himachal', 17],

       ['S2', 'Punjab', 16],

       ['S3', 'Haryana', 18]]

df2 = pd.DataFrame(lst, index=[1, 2, 3],

  columns=['State Code', 'State Name', 'Rank'])

print(df2)

# Arithmetic Operations on DataFrames

print("\nPerforming Arithmetic Operations")

L1 = [[10, 20, 30], [40, 50, 60]]

L2 = [[15, 25, 35], [10, 60, 70]]

D1 = pd.DataFrame(L1)

D2 = pd.DataFrame(L2)

print("\nDATAFRAME D1:\n", D1)

print("\nDATAFRAME D2:\n", D2)

print("\nAddition (D1 + D2):\n", D1 + D2)

print("\nSubtraction (D1 - D2):\n", D1 - D2)

print("\nMultiplication (D1 * D2):\n", D1 * D2)

print("\nInteger Division (D2 // D1):\n", D2 // D1)

# Mean of selected columns

print("\nMean of selected columns in D1:\n", D1.iloc[:, 1:3].mean())