Python Libraries Overview

import os           # file system, environment variables, paths
import sys          # Python runtime info, argv
import math         # mathematical functions and constants
import random       # random number generation
import collections  # Counter, defaultdict, deque, namedtuple
import itertools    # tools for working with iterators
import functools    # lru_cache, reduce, partial
import pathlib      # modern object-oriented file paths
import shutil       # copy, move, delete files and directories
import re           # regular expressions
import json         # JSON encode/decode
import logging      # production-quality logging

# Quick examples
import math
print(math.pi)              # 3.141592653589793
print(math.sqrt(144))       # 12.0
print(math.ceil(4.2))       # 5
print(math.log(100, 10))    # 2.0  — log base 10

import random
print(random.randint(1, 10))           # random int 1–10
print(random.choice(["a","b","c"]))    # random item from list
random.shuffle([1,2,3,4,5])            # shuffle in-place

from collections import Counter, defaultdict
c = Counter("mississippi")
print(c.most_common(3))    # [('s', 4), ('i', 4), ('p', 2)]

d = defaultdict(list)
d["key"].append(1)         # no KeyError — missing key gets default []
print(d)                   # defaultdict(<class 'list'>, {'key': [1]})

import requests

# GET request — fetch JSON from a public API
response = requests.get(
    "https://httpbin.org/get",
    params={"name": "dataplexa"},
    timeout=10          # always set a timeout in production
)

response.raise_for_status()    # raises exception on 4xx/5xx

print("Status  :", response.status_code)
print("URL     :", response.json()["url"])

# POST request — send JSON body
payload = {"username": "alice", "score": 99}
r = requests.post("https://httpbin.org/post", json=payload, timeout=10)
print("Posted  :", r.json()["json"])

# Session — reuse connection, share headers/cookies
session = requests.Session()
session.headers.update({"Authorization": "Bearer my_token"})
# r2 = session.get("https://api.example.com/data")

import pandas as pd   # pd is the universal alias

data = {
    "product": ["notebook", "pen", "desk", "lamp", "chair"],
    "price":   [4.99, 1.50, 89.99, 24.99, 149.99],
    "sold":    [120, 300, 15, 45, 22]
}
df = pd.DataFrame(data)

print(df.head())
print("\nInfo:")
print(f"  Rows: {len(df)}, Columns: {list(df.columns)}")
print(f"  Avg price: ${df['price'].mean():.2f}")

# Computed column
df["revenue"] = df["price"] * df["sold"]
print(f"  Total revenue: ${df['revenue'].sum():.2f}")

# Filter — items priced under $30
affordable = df[df["price"] < 30][["product", "price", "sold"]]
print("\nAffordable items:")
print(affordable.to_string(index=False))

# Sort by revenue descending
print("\nTop earners:")
print(df.sort_values("revenue", ascending=False)[["product","revenue"]].to_string(index=False))

import numpy as np   # np is the universal alias

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

print("Array :", arr)
print("Mean  :", arr.mean())
print("Std   :", arr.std())
print("Sum   :", arr.sum())

# Vectorized math — no loop needed, runs at C speed
print("×2    :", arr * 2)
print(">25   :", arr[arr > 25])    # boolean indexing

# 2D array (matrix)
matrix = np.array([[1, 2], [3, 4]])
print("Det   :", np.linalg.det(matrix))     # -2.0
print("Inv   :\n", np.linalg.inv(matrix))   # matrix inverse

# Common array creation
print(np.zeros(4))           # [0. 0. 0. 0.]
print(np.arange(0, 10, 2))  # [0 2 4 6 8]
print(np.linspace(0,1,5))   # [0.  0.25 0.5  0.75 1. ]

import matplotlib.pyplot as plt

months  = ["Jan", "Feb", "Mar", "Apr", "May", "Jun"]
revenue = [12000, 15400, 13800, 17200, 19500, 21000]
costs   = [9000,  10200, 10500, 11800, 12400, 13500]

fig, axes = plt.subplots(1, 2, figsize=(12, 4))

# Line chart
axes[0].plot(months, revenue, marker="o", color="#7c3aed", label="Revenue", linewidth=2)
axes[0].plot(months, costs,   marker="s", color="#f97316", label="Costs",   linewidth=2)
axes[0].set_title("Revenue vs Costs 2024")
axes[0].legend()
axes[0].grid(True, alpha=0.3)

# Bar chart
profit = [r - c for r, c in zip(revenue, costs)]
axes[1].bar(months, profit, color="#22c55e")
axes[1].set_title("Monthly Profit")
axes[1].set_ylabel("$")

plt.tight_layout()
plt.savefig("charts.png")
print("Charts saved to charts.png")

# Save as app.py — run with: flask --app app run

from flask import Flask, jsonify, request, abort

app = Flask(__name__)

products = [
    {"id": 1, "name": "notebook", "price": 4.99},
    {"id": 2, "name": "pen",      "price": 1.50},
    {"id": 3, "name": "desk",     "price": 89.99},
]

@app.route("/products", methods=["GET"])
def get_products():
    return jsonify(products)

@app.route("/products/<int:pid>", methods=["GET"])
def get_product(pid):
    match = next((p for p in products if p["id"] == pid), None)
    if not match:
        abort(404)
    return jsonify(match)

@app.route("/products", methods=["POST"])
def add_product():
    data = request.get_json()
    data["id"] = max(p["id"] for p in products) + 1
    products.append(data)
    return jsonify(data), 201

# Run: flask --app app run
# GET  http://127.0.0.1:5000/products
# GET  http://127.0.0.1:5000/products/1
# POST http://127.0.0.1:5000/products  {"name":"lamp","price":24.99}

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split, cross_val_score
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, classification_report

iris   = load_iris()
X, y   = iris.data, iris.target

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)

model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

preds = model.predict(X_test)
print("Accuracy        :", accuracy_score(y_test, preds))
print("Feature importances:", model.feature_importances_.round(3))

# Cross-validation — more reliable than a single train/test split
cv_scores = cross_val_score(model, X, y, cv=5)
print(f"CV accuracy: {cv_scores.mean():.3f} ± {cv_scores.std():.3f}")