import pandas as pd

# Question: do students who study more hours score higher?
df = pd.DataFrame({
    "hours": [1, 2, 3, 4, 5, 6, 7, 8],
    "score": [52, 55, 61, 64, 70, 72, 79, 83],
})
print("correlation:", round(df["hours"].corr(df["score"]), 2))
# A strong positive correlation — but correlation is not proof of cause

How related fields differ
Data analytics: what happened and why? (reports, dashboards, SQL)
Data science:   what will happen and what should we do? (statistics, ML, experiments)
Machine learning: algorithms that learn patterns from data
AI: the broad field of making systems perform tasks that need intelligence
In practice, these overlap and teams work together.

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score

# 1. Question: can we identify a flower's species from its measurements?
X, y = load_iris(return_X_y=True)                     # 2. Data
X_tr, X_te, y_tr, y_te = train_test_split(X, y, test_size=0.3, random_state=0)
model = DecisionTreeClassifier(max_depth=3, random_state=0).fit(X_tr, y_tr)   # 3. Model
print("accuracy:", round(accuracy_score(y_te, model.predict(X_te)), 2))      # 4. Evaluate
# 5. Communicate: explain accuracy, limits and how it would be used

Problem statement
Decision to support: ______________
Question: ______________
Who uses the answer: ______________
Success measure: ______________
Data available: ______________
Constraints (time, privacy): ______________

import numpy as np

amounts = np.array([450, 520, 380, 610, 495, 530, 9800, 470])
mean, std = amounts.mean(), amounts.std()
z = (amounts - mean) / std
print("unusual:", amounts[np.abs(z) > 2])   # flags the 9800 transaction
# Real fraud systems use many more features and careful evaluation

This week, notice three examples of data science:
1. App or service: ______  Question it answers: ______
2. App or service: ______  Question it answers: ______
3. App or service: ______  Question it answers: ______
For each, guess what data it uses.

Beginner study plan
Step 1: Python basics
Step 2: pandas and visualisation
Step 3: SQL basics
Step 4: Statistics (averages, spread, correlation, sampling, tests)
Step 5: Machine learning basics with scikit-learn
Step 6: First end-to-end project
Step 7: Communicate results in a short write-up

First project idea: What affects student performance?
Data: a public student performance dataset
Question: which factors relate to higher scores?
Steps: clean → explore charts → correlations → simple model → write-up
Output: notebook + one-page summary with 3 findings and limitations

Core concepts checklist
☐ Mean, median, standard deviation
☐ Correlation vs causation
☐ Train/test split
☐ Overfitting
☐ Accuracy, precision, recall
☐ Baseline models
☐ Data cleaning steps