import numpy as np
import time

nums = list(range(1_000_000))
arr = np.arange(1_000_000)

t = time.time()
squares = [x * x for x in nums]
print("list loop:", round(time.time() - t, 4), "s")

t = time.time()
squares_np = arr * arr
print("numpy    :", round(time.time() - t, 4), "s")

import numpy as np

a = np.array([[1, 2, 3], [4, 5, 6]])
print(a.shape)   # (2, 3)
print(a.dtype)   # int64 on most systems
print(a[1, 2])   # 6
print(a[:, 0])   # [1 4]  first column
print(a.T)       # transpose, shape (3, 2)

import numpy as np

ages = np.array([23, -1, 35, 41, 200, 29])
valid = ages[(ages > 0) & (ages < 120)]
print(valid)            # [23 35 41 29]
print(valid.mean())     # 32.0
print(np.median(valid)) # 32.0

import numpy as np

X = np.array([[50, 3.0], [60, 3.5], [70, 4.0]])
X_std = (X - X.mean(axis=0)) / X.std(axis=0)
print(X_std.round(2))
# each column now has mean 0 and std 1
# broadcasting applied the column stats to every row

import numpy as np
from sklearn.linear_model import LinearRegression

hours = np.array([1, 2, 3, 4, 5])
scores = np.array([52, 58, 65, 70, 78])

X = hours.reshape(-1, 1)   # sklearn needs 2D input
model = LinearRegression().fit(X, scores)
print(model.predict(np.array([[6]])))

import pandas as pd

df = pd.DataFrame({"height": [160, 172, 181], "weight": [55, 70, 82]})
arr = df.to_numpy()
print(type(arr), arr.shape)   # <class 'numpy.ndarray'> (3, 2)
bmi = arr[:, 1] / (arr[:, 0] / 100) ** 2
print(bmi.round(1))

NumPy Topic Checklist
☐ Create arrays: array, arange, linspace, zeros, ones
☐ Read shape, ndim, dtype, size
☐ Indexing and slicing in 1D and 2D
☐ Boolean masks and np.where
☐ Aggregations with axis
☐ Broadcasting rules
☐ reshape, transpose, stack, concatenate
☐ Random numbers with np.random.default_rng
☐ Dot product and matrix multiply (@)
☐ Saving and loading with np.save / np.load

NumPy Exercise Log
Date: ________
Exercise: ________________________
Input shape: ______  Output shape: ______
Functions used: ____________________
Did I use a loop? Yes / No
If yes, vectorised version written? ☐
Time taken: ______
What confused me:
1.
2.

NumPy Mini Project Plan
Dataset: ____________ (CSV with numeric columns)
Goal: summarise and standardise the features

Steps:
1. Load with np.genfromtxt or pandas, convert to array
2. Remove invalid rows with a boolean mask
3. Compute mean, median, std per column
4. Standardise with broadcasting
5. Compute a correlation matrix with np.corrcoef
6. Write findings in a README