Adv-Python Unit 4: Complete Concepts Guide

# Install Pandas
pip install pandas

# Standard import convention
import pandas as pd

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

import pandas as pd

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

# Select one column
print(df["Name"])

# Select multiple columns
print(df[["Name", "Marks"]])

# Select rows using label-based indexing
print(df.loc[0])

# Select rows using integer position
print(df.iloc[0:2])

# Filter rows
high_scorers = df[df["Marks"] > 80]
print(high_scorers)

# Create new column
df["Total"] = df["Marks"] + 10
print(df)

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

import pandas as pd

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)
print(combined)

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")
print(result)

import pandas as pd

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

print(students.head())
print(students.shape)
print(students.info())

# 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())

import numpy as np

arr = np.array([10, 20, 30, 40])
print(arr)
print(type(arr))       # <class 'numpy.ndarray'>
print(arr.dtype)       # int64

import numpy as np

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

print(a.shape)   # (2, 3) — rows and columns
print(a.ndim)    # 2 — number of dimensions
print(a.size)    # 6 — total number of elements
print(a.dtype)   # int64 — data type of elements

┌──────────────┐    ┌──────────────┐    ┌──────────────┐    ┌──────────────┐    ┌──────────────┐
│ 1. Create    │ →  │ 2. Index &   │ →  │ 3. Vectorized│ →  │ 4. Join /    │ →  │ 5. Search /  │
│    ndarray   │    │    Slice     │    │   Operations │    │    Split     │    │  Sort/Filter │
└──────────────┘    └──────────────┘    └──────────────┘    └──────────────┘    └──────────────┘

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

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

import numpy as np

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.]

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]

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

print(np.vstack((x, y)))   # Vertical stacking
print(np.hstack((x, y)))   # Horizontal stacking

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])]

import numpy as np

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

import numpy as np

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

import numpy as np

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

filtered = a[a > 30]
print(filtered)   # [45, 50]

import numpy as np

print(np.random.randint(1, 10))        # One random integer
print(np.random.rand(3))               # 3 random floats from 0 to 1
print(np.random.randint(1, 100, 5))    # 5 random integers

import numpy as np

np.random.seed(10)
print(np.random.randint(1, 100, 5))   # Same output every time

┌──────────────┐    ┌──────────────┐    ┌──────────────┐    ┌──────────────┐    ┌──────────────┐
│ 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

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

plt.plot(x, y)
plt.title("Simple Line Plot")
plt.xlabel("X Values")
plt.ylabel("Y Values")
plt.show()

import matplotlib.pyplot as plt

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

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

import matplotlib.pyplot as plt

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

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

import matplotlib.pyplot as plt

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.xlabel("Study Hours")
plt.ylabel("Marks")
plt.show()

import matplotlib.pyplot as plt

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()

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

# Create sample data
students = pd.DataFrame({
    "Name": ["Amit", "Ravi", "Neha", "Sara", "John"],
    "Python": [78, 85, 92, 66, 74],
    "Maths": [80, 70, 88, 60, 79]
})

# Calculate total and average using Pandas/NumPy
students["Total"] = students["Python"] + students["Maths"]
students["Average"] = np.round(students["Total"] / 2, 2)

print(students)
print(students.describe())

# Plot average marks
plt.bar(students["Name"], students["Average"])
plt.title("Average Marks of Students")
plt.xlabel("Student")
plt.ylabel("Average Marks")
plt.show()

PANDAS, NUMPY, AND MATPLOTLIB
│
├── Introduction
│   ├── Pandas → Tabular data
│   ├── NumPy → Numerical computation
│   └── Matplotlib → Visualization
│
├── Pandas
│   ├── Series (1D labelled array)
│   ├── DataFrame (2D labelled table)
│   ├── Inspection: head(), tail(), shape, info(), describe()
│   ├── Selection: df["col"], loc[], iloc[]
│   ├── Cleaning: dropna(), fillna(), drop_duplicates()
│   ├── Combining: concat(), merge(), join()
│   └── I/O: read_csv(), to_csv(), read_json(), to_json()
│
├── NumPy
│   ├── ndarray object
│   ├── Creation: array(), zeros(), ones(), arange(), linspace()
│   ├── Attributes: shape, ndim, size, dtype
│   ├── Indexing and slicing
│   ├── Operations: concatenate(), vstack(), hstack(), array_split()
│   ├── Search: where()
│   ├── Sort: sort()
│   ├── Filter: boolean masks
│   └── Random: rand(), randint(), choice(), seed()
│
├── Web Scraping
│   ├── Workflow: Request → Parse → Extract → Store
│   ├── Tools: requests, BeautifulSoup
│   └── Ethics: robots.txt, terms of service, privacy
│
└── Matplotlib
    ├── pyplot module
    ├── Chart types: line, bar, histogram, scatter, pie
    ├── Customization: title, labels, legend
    └── Workflow: Prepare → Create → Plot → Customize → Show/Save