Essential Python Recursion and Pandas Data Analysis

Recursive Functions in Python

def range_sum(num_list, start, end):
    if start > end:          # Base case
        return 0
    else:                    # Recursive case
        return num_list[start] + range_sum(num_list, start + 1, end)

numbers = [2, 4, 6, 8, 10]
print(range_sum(numbers, 1, 3))  # Expected output: 18

Tower of Hanoi

def hanoi(n, from_peg, to_peg, temp_peg):
    if n > 0:
        # Step 1: Move n-1 discs to temp peg
        hanoi(n - 1, from_peg, temp_peg, to_peg)
        # Step 2: Move the bottom disc
        print(f"Move disc from peg {from_peg} to peg {to_peg}")
        # Step 3: Move n-1 discs from temp peg to target peg
        hanoi(n - 1, temp_peg, to_peg, from_peg)

Greatest Common Divisor

def gcd(x, y):
    if x % y == 0:
        return y
    else:
        return gcd(y, x % y)

print(gcd(48, 18))

Fibonacci Sequence

def fibonacci(n):
    if n <= 1:
        return n
    else:
        return fibonacci(n - 1) + fibonacci(n - 2)

print(fibonacci(5))

Factorial Calculation

def factorial(n):
    if n == 0:       # Base case
        return 1
    else:            # Recursive case
        return n * factorial(n - 1)

print(factorial(4))

Pandas Data Analysis

import pandas as pd

# From CSV file
df = pd.read_csv("data.csv")

# Look at first rows
print(df.head())

# Check structure
print(df.info())

Accessing Data

• df['column']: One column (Series)
• df[['col1', 'col2']]: Multiple columns (DataFrame)
• df.loc[0:3, 'col1']: Label-based selection
• df.iloc[0:3, 0:2]: Position-based selection

Filtering Rows

df[df['age'] > 30]
df[(df['age'] > 30) & (df['city'] == 'Toronto')]

Creating Columns

df['double_age'] = df['age'] * 2
df['bonus'] = df['salary'].apply(lambda x: x * 0.1)

Merging and Joining

pd.merge(df1, df2, on='id', how='inner')
pd.merge(df1, df2, left_on='A', right_on='B', how='outer')

Grouping Data

df.groupby('department')['salary'].mean()
df.groupby('category').agg({'sales': 'sum', 'profit': 'mean'})

Practical Example

Get the rows for people in Toronto who are older than 30, returning only the name and spend columns:

import pandas as pd

df = pd.DataFrame({
    "name": ["Ava", "Ben", "Chen", "Devi", "Eli", "Fatima"],
    "city": ["Toronto", "Ottawa", "Toronto", "Montreal", "Toronto", "Calgary"],
    "age": [28, 34, 41, 22, 36, 29],
    "spend": [120, 80, 200, 60, 150, 90]
})

df[(df['city'] == 'Toronto') & (df['age'] > 30)][['name', 'spend']]