NumPy & Pandas Basics

# Import NumPy library
import numpy as np

# Create a 1D NumPy array from a Python list
arr = np.array([10, 20, 30, 40, 50])
print("Original array:", arr)

# Create a 2D array (matrix) of shape (3, 3)
matrix = np.array([[1, 2, 3],
                   [4, 5, 6],
                   [7, 8, 9]])
print("2D Matrix:
", matrix)

# Access elements: element at row 1, column 2
elem = matrix[1, 2]
print("Element at (1, 2):", elem)

# Slicing: get first two rows and last two columns
slice_sub = matrix[:2, 1:]
print("Sliced submatrix:
", slice_sub)

# Reshape array: flatten matrix into 1D array
flat = matrix.reshape(-1)
print("Flattened array:", flat)

# Broadcasting: add a scalar to entire array
broadcasted = matrix + 10
print("After adding 10 to each element:
", broadcasted)

# Element-wise multiplication
multiplied = matrix * matrix
print("Element-wise squared matrix:
", multiplied)
    

import pandas as pd

# Create a Pandas Series from a list with custom indices
data = [100, 200, 300, 400]
index_labels = ['a', 'b', 'c', 'd']
series = pd.Series(data, index=index_labels)
print("Series:
", series)

# Access elements by label and position
print("Element with label 'b':", series['b'])
print("Element at position 2:", series.iloc[2])

# Create a DataFrame from a dictionary of lists
data_dict = {
    'Name': ['Alice', 'Bob', 'Charlie'],
    'Age': [25, 30, 35],
    'Salary': [70000, 80000, 90000]
}
df = pd.DataFrame(data_dict)
print("
DataFrame:
", df)

# Select a column (returns a Series)
ages = df['Age']
print("
Ages column:
", ages)

# Select multiple columns (returns a DataFrame)
subset = df[['Name', 'Salary']]
print("
Subset DataFrame:
", subset)

# Filter rows where Age > 28
filtered = df[df['Age'] > 28]
print("
Filtered DataFrame (Age > 28):
", filtered)

# Using loc and iloc for selection
print("
Select row with label 1 using loc:
", df.loc[1])
print("
Select first row using iloc:
", df.iloc[0])
    

import pandas as pd

# Sample sales data
sales_data = {
    'Region': ['North', 'South', 'East', 'West', 'North', 'South'],
    'Salesperson': ['Alice', 'Bob', 'Charlie', 'David', 'Eva', 'Frank'],
    'Sales': [250, 150, 200, 300, 400, 100]
}
df = pd.DataFrame(sales_data)

# Group by 'Region' and sum the sales
region_sales = df.groupby('Region')['Sales'].sum()
print("Total sales per region:
", region_sales)

# Group by 'Region' and calculate multiple aggregations
agg_funcs = df.groupby('Region')['Sales'].agg(['sum', 'mean', 'max'])
print("
Aggregated sales stats by region:
", agg_funcs)

# Create a pivot table for Sales by Region and Salesperson
pivot = pd.pivot_table(df, values='Sales', index='Region', columns='Salesperson', fill_value=0)
print("
Pivot table:
", pivot)
    

import pandas as pd

# DataFrame 1: Employee info
df1 = pd.DataFrame({
    'EmployeeID': [1, 2, 3],
    'Name': ['Alice', 'Bob', 'Charlie']
})

# DataFrame 2: Employee department
df2 = pd.DataFrame({
    'EmployeeID': [2, 3, 4],
    'Department': ['HR', 'IT', 'Finance']
})

# Merge on EmployeeID (inner join)
merged_inner = pd.merge(df1, df2, on='EmployeeID')
print("Inner Merge:
", merged_inner)

# Merge with outer join to keep all records
merged_outer = pd.merge(df1, df2, on='EmployeeID', how='outer')
print("
Outer Merge:
", merged_outer)

# Concatenate DataFrames vertically
df3 = pd.DataFrame({
    'EmployeeID': [5],
    'Name': ['David']
})
concatenated = pd.concat([df1, df3], ignore_index=True)
print("
Concatenated DataFrame:
", concatenated)