import pandas as pd

marks = pd.Series([78, 85, 92, 66], index=["Amit", "Ravi", "Neha", "Sara"])
print(marks)
print(marks["Neha"])   # 92

Amit    78
Ravi    85
Neha    92
Sara    66
dtype: int64
92

import pandas as pd

data = {
    "Name": ["Amit", "Ravi", "Neha", "Sara"],
    "Age": [21, 22, 20, 23],
    "Marks": [78, 85, 92, 66]
}
df = pd.DataFrame(data)
print(df)

   Name  Age  Marks
0  Amit   21     78
1  Ravi   22     85
2  Neha   20     92
3  Sara   23     66

import pandas as pd

data = {
    "Name": ["Amit", "Ravi", "Neha", "Sara"],
    "Age": [21, 22, 20, 23],
    "Marks": [78, 85, 92, 66]
}
df = pd.DataFrame(data)

# Select row with label 0
print(df.loc[0])

# Select rows 0 to 2 (inclusive)
print(df.loc[0:2])

# Select specific rows and columns
print(df.loc[0:2, ["Name", "Marks"]])

# Conditional selection
print(df.loc[df["Marks"] > 80])

# Select first row
print(df.iloc[0])

# Select rows 0 to 2 (exclusive of 3)
print(df.iloc[0:3])

# Select rows 0-2, columns 0-1
print(df.iloc[0:3, 0:2])

# Select last row
print(df.iloc[-1])

df.dropna(axis=0, how='any', thresh=None, subset=None, inplace=False)

import pandas as pd

data = {"Name": ["Amit", "Ravi", "Neha"], "Marks": [78, None, 92]}
df = pd.DataFrame(data)

print(df.dropna())         # Remove rows with any NaN
print(df.dropna(axis=1))   # Remove columns with any NaN

df.fillna(value=None, method=None, axis=None, inplace=False)

print(df.fillna(0))              # Replace NaN with 0
print(df.fillna(df.mean()))      # Replace with column mean
print(df.fillna(method='ffill')) # Forward fill

import pandas as pd

data = {"Name": ["Amit", "Ravi", "Neha"], "Marks": [78, None, 92]}
df = pd.DataFrame(data)

print(df.isnull())        # Check missing values
print(df.dropna())        # Remove rows with missing values
print(df.fillna(0))       # Replace missing values with 0
print(df.fillna(df["Marks"].mean()))  # Replace with mean

import pandas as pd

# Read a CSV file
students = pd.read_csv("students.csv")

# Inspect the data
print(students.head())     # First 5 rows
print(students.shape)      # (rows, columns)
print(students.info())     # Column types and non-null counts
print(students.describe()) # Statistical summary

# Save a DataFrame to a CSV file
students.to_csv("cleaned_students.csv", index=False)

import pandas as pd

# Read a JSON file
orders = pd.read_json("orders.json")
print(orders.head())

# Save a DataFrame to a JSON file
orders.to_json("cleaned_orders.json", orient="records", indent=4)

import numpy as np

arr = np.array([10, 20, 30, 40])
print(arr)          # [10 20 30 40]
print(type(arr))    # <class 'numpy.ndarray'>

a = np.array([[1, 2, 3], [4, 5, 6]])
print(a.shape)   # (2, 3) — 2 rows, 3 columns

print(a.ndim)    # 2 — two-dimensional array

print(a.size)    # 6 — 2 × 3 = 6 elements

print(a.dtype)   # int64 (or int32 depending on platform)

import numpy as np

a = np.array([[1, 2, 3], [4, 5, 6]])

print(a.shape)   # (2, 3)
print(a.ndim)    # 2
print(a.size)    # 6
print(a.dtype)   # int64

import numpy as np

a = np.array([10, 20, 30, 40, 50])

print(a[0])      # 10 — first element
print(a[-1])     # 50 — last element
print(a[1:4])    # [20, 30, 40] — elements from index 1 to 3
print(a[:3])     # [10, 20, 30] — first three elements
print(a[::2])    # [10, 30, 50] — every second element
print(a[::-1])   # [50, 40, 30, 20, 10] — reversed

import numpy as np

matrix = np.array([[1, 2, 3],
                   [4, 5, 6],
                   [7, 8, 9]])

print(matrix[0, 0])       # 1 — row 0, column 0
print(matrix[1, 2])       # 6 — row 1, column 2
print(matrix[:, 1])       # [2, 5, 8] — all rows, column 1
print(matrix[0:2, 1:3])   # Sub-array [[2, 3], [5, 6]]
print(matrix[1, :])       # [4, 5, 6] — row 1, all columns
print(matrix[:, 0])       # [1, 4, 7] — all rows, column 0

a = np.array([1, 2, 3, 4, 5])
b = a[1:4]     # b is a view
b[0] = 99
print(a)       # [1, 99, 3, 4, 5] — original modified

b = a[1:4].copy()

import numpy as np

a = np.array([1, 2, 3])
b = np.array([4, 5, 6])

joined = np.concatenate((a, b))
print(joined)   # [1 2 3 4 5 6]

x = np.array([[1, 2], [3, 4]])
y = np.array([[5, 6], [7, 8]])

print(np.concatenate((x, y), axis=0))  # Vertical (rows)
print(np.concatenate((x, y), axis=1))  # Horizontal (columns)

x = np.array([[1, 2], [3, 4]])
y = np.array([[5, 6], [7, 8]])

print(np.vstack((x, y)))
# [[1 2]
#  [3 4]
#  [5 6]
#  [7 8]]

print(np.hstack((x, y)))
# [[1 2 5 6]
#  [3 4 7 8]]

import numpy as np

a = np.array([1, 2, 3, 4, 5, 6])

parts = np.array_split(a, 3)
print(parts)
# [array([1, 2]), array([3, 4]), array([5, 6])]

parts = np.split(a, 3)
print(parts)   # Same as above but requires equal division

matrix = np.array([[1, 2, 3, 4], [5, 6, 7, 8]])

print(np.hsplit(matrix, 2))   # Split horizontally
print(np.vsplit(matrix, 2))   # Split vertically

a = np.array([1, 2, 3, 4, 5, 6])
reshaped = a.reshape(2, 3)
print(reshaped)
# [[1 2 3]
#  [4 5 6]]

import numpy as np

# Joining
sem1 = np.array([85, 78, 92])
sem2 = np.array([88, 82, 95])
all_marks = np.concatenate((sem1, sem2))
print("Joined:", all_marks)

# Splitting
data = np.array([10, 20, 30, 40, 50, 60])
parts = np.array_split(data, 3)
print("Split:", parts)

# Reshaping
matrix = np.arange(1, 13).reshape(3, 4)
print("Reshaped:\n", matrix)

Joined: [85 78 92 88 82 95]
Split: [array([10, 20]), array([30, 40]), array([50, 60])]
Reshaped:
 [[ 1  2  3  4]
  [ 5  6  7  8]
  [ 9 10 11 12]]

import numpy as np

a = np.array([10, 20, 30, 20, 40])
result = np.where(a == 20)
print(result)   # (array([1, 3]),)

print(np.where(a > 25))   # (array([2, 4]),)

sorted_arr = np.array([10, 20, 30, 40, 50])
print(np.searchsorted(sorted_arr, 35))   # 3 (insert before index 3)

a = np.array([10, 50, 30, 20])
print(np.argmax(a))   # 1 (index of 50)
print(np.argmin(a))   # 0 (index of 10)

import numpy as np

a = np.array([40, 10, 30, 20])
print(np.sort(a))   # [10 20 30 40]

a = np.array([40, 10, 30, 20])
a.sort()
print(a)   # [10 20 30 40]

matrix = np.array([[3, 1, 2], [6, 5, 4]])
print(np.sort(matrix, axis=0))   # Sort each column
print(np.sort(matrix, axis=1))   # Sort each row

a = np.array([40, 10, 30, 20])
print(np.argsort(a))   # [1 3 2 0]

import numpy as np

a = np.array([10, 25, 30, 45, 50])

# Filter values greater than 30
filtered = a[a > 30]
print(filtered)   # [45 50]

# Filter with multiple conditions
filtered = a[(a > 20) & (a < 50)]
print(filtered)   # [25 30 45]

# Filter even numbers
evens = a[a % 2 == 0]
print(evens)   # [10 30 50]

mask = a > 30
print(mask)   # [False False False  True  True]
print(a[mask])  # [45 50]

import numpy as np

marks = np.array([78, 85, 92, 66, 74, 88, 95, 60])

# Searching
print("Students scoring 85:", np.where(marks == 85))

# Sorting
print("Sorted marks:", np.sort(marks))
print("Ranking indices:", np.argsort(marks))

# Filtering
print("Marks above 80:", marks[marks > 80])
print("Marks between 70 and 90:", marks[(marks >= 70) & (marks <= 90)])

# Top scorer
print("Top scorer marks:", marks.max())
print("Top scorer index:", marks.argmax())

Students scoring 85: (array([1]),)
Sorted marks: [60 66 74 78 85 88 92 95]
Ranking indices: [7 3 4 0 1 5 2 6]
Marks above 80: [85 92 88 95]
Marks between 70 and 90: [78 85 74 88]
Top scorer marks: 95
Top scorer index: 6

┌──────────────┐    ┌──────────────┐    ┌──────────────┐    ┌──────────────┐    ┌──────────────┐
│ 1. Send HTTP │ →  │ 2. Download  │ →  │ 3. Parse and │ →  │ 4. Clean and │ →  │ 5. Store or  │
│   Request    │    │    HTML      │    │ Extract Data │    │  Structure   │    │  Export Data │
└──────────────┘    └──────────────┘    └──────────────┘    └──────────────┘    └──────────────┘

import requests
from bs4 import BeautifulSoup

url = "https://example.com"
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")

print(soup.title.text)

┌──────────────┐    ┌──────────────┐    ┌──────────────┐    ┌──────────────┐    ┌──────────────┐
│ 1. Prepare   │ →  │ 2. Create    │ →  │ 3. Plot Data │ →  │ 4. Customize │ →  │ 5. Show or   │
│    Data      │    │   Figure     │    │              │    │    Plot      │    │    Save      │
└──────────────┘    └──────────────┘    └──────────────┘    └──────────────┘    └──────────────┘

import matplotlib.pyplot as plt

# Step 1: Prepare Data
x = [1, 2, 3, 4, 5]
y = [10, 15, 13, 18, 20]

# Step 2: Create Figure (optional)
plt.figure(figsize=(8, 5))

# Step 3: Plot Data
plt.plot(x, y)

# Step 4: Customize Plot
plt.title("Simple Line Plot")
plt.xlabel("X Values")
plt.ylabel("Y Values")

# Step 5: Show or Save
plt.show()

subjects = ["Python", "Maths", "DBMS", "OS"]
marks = [85, 78, 92, 74]
plt.bar(subjects, marks)
plt.title("Marks by Subject")
plt.show()

marks = [45, 56, 67, 78, 89, 90, 72, 63, 55, 81]
plt.hist(marks, bins=5)
plt.title("Distribution of Marks")
plt.show()

hours = [1, 2, 3, 4, 5, 6]
marks = [40, 50, 55, 65, 75, 85]
plt.scatter(hours, marks)
plt.title("Study Hours vs Marks")
plt.show()

labels = ["Python", "Java", "C++", "R"]
students = [40, 25, 20, 15]
plt.pie(students, labels=labels, autopct="%1.1f%%")
plt.title("Programming Language Preference")
plt.show()

┌──────────────┐    ┌──────────────┐    ┌──────────────┐    ┌──────────────┐    ┌──────────────┐
│ 1. Import    │ →  │ 2. Create    │ →  │ 3. Clean &   │ →  │ 4. Combine   │ →  │ 5. Analyze   │
│    Data      │    │  Series/DF   │    │   Transform  │    │   Datasets   │    │  & Export    │
└──────────────┘    └──────────────┘    └──────────────┘    └──────────────┘    └──────────────┘

import pandas as pd

# Read CSV
df = pd.read_csv("students.csv")

# Read JSON
df = pd.read_json("students.json")

# Read Excel
df = pd.read_excel("students.xlsx")

import pandas as pd

data = {
    "Name": ["Amit", "Ravi", "Neha", "Sara"],
    "Age": [21, 22, 20, 23],
    "Marks": [78, 85, 92, 66]
}
df = pd.DataFrame(data)

print(df.head())
print(df.shape)
print(df.info())
print(df.describe())

# Detect
print(df.isnull())

# Remove
df = df.dropna()

# Fill
df = df.fillna(0)
df = df.fillna(df.mean())

df = df.drop_duplicates()

# Select columns
df["Name"]
df[["Name", "Marks"]]

# Select rows by label
df.loc[0]
df.loc[df["Marks"] > 80]

# Select rows by position
df.iloc[0:3, 1:3]

df["Total"] = df["Python"] + df["Maths"]
df["Average"] = df["Total"] / 2
df["Grade"] = df["Average"].apply(lambda x: "A" if x > 85 else "B")

high_scorers = df[df["Marks"] > 80]
low_attendance = df[df["Attendance"] < 75]

df = df.sort_values("Marks", ascending=False)

dept_avg = df.groupby("Department")["Marks"].mean()
dept_summary = df.groupby("Department").agg({
    "Marks": ["mean", "max", "min"],
    "Attendance": "mean"
})

df1 = pd.DataFrame({"ID": [1, 2], "Name": ["Amit", "Ravi"]})
df2 = pd.DataFrame({"ID": [3, 4], "Name": ["Neha", "Sara"]})
combined = pd.concat([df1, df2], ignore_index=True)

marks = pd.DataFrame({"ID": [1, 2, 3], "Marks": [78, 85, 92]})
students = pd.DataFrame({"ID": [1, 2, 3], "Name": ["Amit", "Ravi", "Neha"]})
result = pd.merge(students, marks, on="ID")

a = pd.DataFrame({"Marks": [78, 85]}, index=[1, 2])
b = pd.DataFrame({"Name": ["Amit", "Ravi"]}, index=[1, 2])
joined = a.join(b)

df.to_csv("cleaned_students.csv", index=False)

df.to_json("cleaned_students.json", orient="records", indent=4)

df.to_excel("cleaned_students.xlsx", index=False)

import pandas as pd

# Step 1: Load
df = pd.read_csv("students.csv")

# Step 2: Inspect
print(df.head())
print(df.info())

# Step 3: Clean
df = df.dropna()
df = df.drop_duplicates()

# Step 4: Transform
df["Total"] = df["Internal"] + df["External"]
df["Average"] = df["Total"] / 2

# Step 5: Filter
top = df[df["Average"] > 80]

# Step 6: Group
dept_avg = df.groupby("Department")["Average"].mean()

# Step 7: Combine
extra = pd.read_csv("extra_students.csv")
combined = pd.concat([df, extra], ignore_index=True)

# Step 8: Export
combined.to_csv("final_results.csv", index=False)

print("Analysis complete.")

import numpy as np

a = np.array([10, 20, 30, 40])
b = np.zeros(5)
c = np.ones((2, 3))
d = np.arange(1, 10, 2)
e = np.linspace(0, 1, 5)
f = np.eye(3)

a = np.array([[1, 2, 3], [4, 5, 6]])
print(a.shape)   # (2, 3)
print(a.ndim)    # 2
print(a.size)    # 6
print(a.dtype)   # int64

a = np.array([10, 20, 30, 40, 50])
print(a[0])      # 10
print(a[-1])     # 50
print(a[1:4])    # [20 30 40]
print(a[::2])    # [10 30 50]

matrix = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
print(matrix[0, 0])       # 1
print(matrix[1, 2])       # 6
print(matrix[:, 1])       # [2 5 8]
print(matrix[0:2, 1:3])   # [[2 3], [5 6]]

a = np.array([10, 20, 30])
b = np.array([1, 2, 3])

print(a + b)   # [11 22 33]
print(a - b)   # [9 18 27]
print(a * b)   # [10 40 90]
print(a / b)   # [10. 10. 10.]
print(a ** 2)  # [100 400 900]

a = np.array([1, 2, 3])
b = np.array([4, 5, 6])
print(np.concatenate((a, b)))   # [1 2 3 4 5 6]

x = np.array([[1, 2], [3, 4]])
y = np.array([[5, 6], [7, 8]])
print(np.vstack((x, y)))
print(np.hstack((x, y)))

a = np.array([1, 2, 3, 4, 5, 6])
print(np.array_split(a, 3))
# [array([1, 2]), array([3, 4]), array([5, 6])]

a = np.array([10, 20, 30, 20, 40])
print(np.where(a == 20))   # (array([1, 3]),)
print(np.argmax(a))        # 4
print(np.argmin(a))        # 0

a = np.array([40, 10, 30, 20])
print(np.sort(a))       # [10 20 30 40]
print(np.argsort(a))    # [1 3 2 0]

a = np.array([10, 25, 30, 45, 50])
print(a[a > 30])              # [45 50]
print(a[(a > 20) & (a < 50)]) # [25 30 45]
print(a[a % 2 == 0])          # [10 30 50]

np.random.seed(10)
print(np.random.randint(1, 100, 5))   # Same every time
print(np.random.rand(3))              # 3 random floats
print(np.random.choice([1, 2, 3, 4])) # Random selection

import matplotlib.pyplot as plt

┌──────────────┐    ┌──────────────┐    ┌──────────────┐    ┌──────────────┐    ┌──────────────┐
│ 1. Prepare   │ →  │ 2. Create    │ →  │ 3. Plot Data │ →  │ 4. Customize │ →  │ 5. Show or   │
│    Data      │    │   Figure     │    │              │    │    Plot      │    │    Save      │
└──────────────┘    └──────────────┘    └──────────────┘    └──────────────┘    └──────────────┘

import matplotlib.pyplot as plt

x = [1, 2, 3, 4, 5]
y = [10, 15, 13, 18, 20]

plt.plot(x, y, marker='o', color='blue')
plt.title("Simple Line Plot")
plt.xlabel("X Values")
plt.ylabel("Y Values")
plt.grid(True, alpha=0.3)
plt.show()

subjects = ["Python", "Maths", "DBMS", "OS"]
marks = [85, 78, 92, 74]

plt.bar(subjects, marks, color='steelblue')
plt.title("Marks by Subject")
plt.xlabel("Subject")
plt.ylabel("Marks")
plt.show()

marks = [45, 56, 67, 78, 89, 90, 72, 63, 55, 81]

plt.hist(marks, bins=5, color='green', edgecolor='black')
plt.title("Distribution of Marks")
plt.xlabel("Marks Range")
plt.ylabel("Number of Students")
plt.show()

hours = [1, 2, 3, 4, 5, 6]
marks = [40, 50, 55, 65, 75, 85]

plt.scatter(hours, marks, color='red')
plt.title("Study Hours vs Marks")
plt.xlabel("Study Hours")
plt.ylabel("Marks")
plt.show()

labels = ["Python", "Java", "C++", "R"]
students = [40, 25, 20, 15]

plt.pie(students, labels=labels, autopct="%1.1f%%")
plt.title("Programming Language Preference")
plt.show()

┌──────────────┐    ┌──────────────┐    ┌──────────────┐    ┌──────────────┐
│ 1. Load CSV  │ →  │ 2. Clean &   │ →  │ 3. Compute   │ →  │ 4. Visualize │
│  (Pandas)    │    │  Transform   │    │  (NumPy)     │    │  (Matplotlib)│
└──────────────┘    └──────────────┘    └──────────────┘    └──────────────┘

Name,Department,Internal,External,Attendance
Amit,CSE,25,60,85
Ravi,CSE,22,55,78
Neha,ECE,28,65,92
Sara,ECE,20,50,70
John,MECH,24,58,88
Priya,CSE,27,62,95
Arjun,MECH,18,45,65
Meena,ECE,26,60,80

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

# ─────────────────────────────────────────────
# Step 1: Load Data (Pandas)
# ─────────────────────────────────────────────
df = pd.read_csv("students.csv")

print("=== First 5 rows ===")
print(df.head())

print("\n=== Data Info ===")
print(df.info())

print("\n=== Statistical Summary ===")
print(df.describe())

# ─────────────────────────────────────────────
# Step 2: Clean and Transform Data (Pandas)
# ─────────────────────────────────────────────
# Check for missing values
print("\n=== Missing Values ===")
print(df.isnull().sum())

# Remove duplicates
df = df.drop_duplicates()

# Create new columns
df["Total"] = df["Internal"] + df["External"]
df["Average"] = np.round(df["Total"] / 2, 2)

# Grade assignment
def assign_grade(avg):
    if avg >= 85:
        return "A"
    elif avg >= 70:
        return "B"
    elif avg >= 55:
        return "C"
    else:
        return "D"

df["Grade"] = df["Average"].apply(assign_grade)

print("\n=== Transformed Data ===")
print(df)

# ─────────────────────────────────────────────
# Step 3: Numerical Operations (NumPy)
# ─────────────────────────────────────────────
mean_avg = np.mean(df["Average"])
median_avg = np.median(df["Average"])
std_avg = np.std(df["Average"])
max_avg = np.max(df["Average"])
min_avg = np.min(df["Average"])

print("\n=== Statistical Measures (NumPy) ===")
print(f"Mean Average:{mean_avg:.2f}")
print(f"Median Average:{median_avg:.2f}")
print(f"Std Deviation:{std_avg:.2f}")
print(f"Max Average:{max_avg:.2f}")
print(f"Min Average:{min_avg:.2f}")

# Filter top performers
top = df[df["Average"] > 80]
print(f"\nTop performers ({len(top)}):")
print(top[["Name", "Average", "Grade"]])

# Filter low attendance
low_att = df[df["Attendance"] < 75]
print(f"\nLow attendance ({len(low_att)}):")
print(low_att[["Name", "Attendance"]])

# ─────────────────────────────────────────────
# Step 4: Grouping and Aggregation (Pandas)
# ─────────────────────────────────────────────
dept_avg = df.groupby("Department")["Average"].mean().reset_index()
print("\n=== Department-wise Average ===")
print(dept_avg)

# ─────────────────────────────────────────────
# Step 5: Visualization (Matplotlib)
# ─────────────────────────────────────────────
fig, axes = plt.subplots(2, 2, figsize=(14, 10))

# Chart 1: Bar chart — Average marks by student
axes[0, 0].bar(df["Name"], df["Average"], color="steelblue")
axes[0, 0].axhline(y=mean_avg, color="red", linestyle="--", label=f"Mean ={mean_avg:.1f}")
axes[0, 0].set_title("Average Marks by Student")
axes[0, 0].set_xlabel("Student")
axes[0, 0].set_ylabel("Average Marks")
axes[0, 0].legend()
axes[0, 0].tick_params(axis="x", rotation=45)

# Chart 2: Histogram — Distribution of averages
axes[0, 1].hist(df["Average"], bins=5, color="green", edgecolor="black")
axes[0, 1].set_title("Distribution of Average Marks")
axes[0, 1].set_xlabel("Average Marks")
axes[0, 1].set_ylabel("Number of Students")

# Chart 3: Scatter plot — Attendance vs Average
axes[1, 0].scatter(df["Attendance"], df["Average"], color="red", s=80)
axes[1, 0].set_title("Attendance vs Average Marks")
axes[1, 0].set_xlabel("Attendance (%)")
axes[1, 0].set_ylabel("Average Marks")
axes[1, 0].grid(True, alpha=0.3)

# Chart 4: Bar chart — Department-wise average
axes[1, 1].bar(dept_avg["Department"], dept_avg["Average"], color="purple")
axes[1, 1].set_title("Department-wise Average Marks")
axes[1, 1].set_xlabel("Department")
axes[1, 1].set_ylabel("Average Marks")

plt.tight_layout()
plt.savefig("student_performance.png")
plt.show()

# ─────────────────────────────────────────────
# Step 6: Export Results (Pandas)
# ─────────────────────────────────────────────
df.to_csv("analyzed_students.csv", index=False)
dept_avg.to_csv("department_averages.csv", index=False)

print("\n=== Analysis Complete ===")
print("Files saved: student_performance.png, analyzed_students.csv, department_averages.csv")

=== First 5 rows ===
    Name Department  Internal  External  Attendance
0   Amit        CSE        25        60          85
1   Ravi        CSE        22        55          78
2   Neha        ECE        28        65          92
3   Sara        ECE        20        50          70
4   John       MECH        24        58          88

=== Statistical Measures (NumPy) ===
Mean Average:   71.75
Median Average: 72.50
Std Deviation:  11.36
Max Average:    89.00
Min Average:    52.50

=== Department-wise Average ===
  Department  Average
0        CSE    75.00
1        ECE    72.75
2       MECH    66.25

┌──────────────┐    ┌──────────────┐    ┌──────────────┐    ┌──────────────┐    ┌──────────────┐
│ 1. Send HTTP │ →  │ 2. Download  │ →  │ 3. Parse and │ →  │ 4. Clean and │ →  │ 5. Store or  │
│   Request    │    │    HTML      │    │ Extract Data │    │  Structure   │    │  Export Data │
└──────────────┘    └──────────────┘    └──────────────┘    └──────────────┘    └──────────────┘

import requests
from bs4 import BeautifulSoup

url = "https://example.com"
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")

# Extract title
print(soup.title.text)

# Extract all links
for link in soup.find_all("a"):
    print(link.get("href"))

# Extract all paragraphs
for p in soup.find_all("p"):
    print(p.text)

import requests
from bs4 import BeautifulSoup
import time

headers = {"User-Agent": "Mozilla/5.0 (educational scraper)"}

for page in range(1, 10):
    url = f"https://example.com/page{page}"
    try:
        response = requests.get(url, headers=headers, timeout=10)
        response.raise_for_status()
        soup = BeautifulSoup(response.text, "html.parser")
        print(f"Page{page}:{soup.title.text}")
        time.sleep(2)   # Respectful delay
    except requests.RequestException as e:
        print(f"Error on page{page}:{e}")

import pandas as pd

df = pd.read_csv("student_performance.csv")
print(df.head())
print(df.shape)
print(df.info())
print(df.describe())
print(df.isnull().sum())

# Create Total column
df["Total"] = df["Internal Marks"] + df["External Marks"]

# Create Average column
df["Average"] = df["Total"] / 2

# Alternative using NumPy for rounding
import numpy as np
df["Average"] = np.round(df["Total"] / 2, 2)

low_attendance = df[df["Attendance"] < 75]
print(low_attendance[["Name", "Department", "Attendance"]])

# Count
print(f"Students with low attendance:{len(low_attendance)}")

# Save to file
low_attendance.to_csv("low_attendance.csv", index=False)