# Let's start with a simple regression: Predicting kitten weight from age.
ages = [1, 2, 3, 4, 5]  # months
weights = [300, 400, 500, 600, 700]  # grams

# Let's look at our data side by side.
for i in range(len(ages)):
    print("Kitten age:", ages[i], "months - Weight:", weights[i], "grams")
    

# Now, let's make a simple prediction.
def predict_weight(age):
    # We notice weight increases by about 100g per month.
    return 200 + age * 100

predicted = predict_weight(6)
print("Predicted weight for 6 month kitten:", predicted, "grams")

# You can try it yourself!
user_age = int(input("Enter kitten's age in months: "))
print("Guessing the kitten's weight:", predict_weight(user_age), "grams")

# If you want to adjust the rule, change the formula in predict_weight.
# For example, what if kittens gain 120g per month?
def predict_weight_v2(age):
    return 180 + age * 120

print("6 months, new formula:", predict_weight_v2(6), "grams")

# Let's switch to classification: Is a fruit an apple or an orange?
colors = ['red', 'green', 'orange', 'red', 'orange']
labels = ['apple', 'apple', 'orange', 'apple', 'orange']

# Let's create a simple rule to guess: If it is orange, call it orange, otherwise apple.
def classify_fruit(color):
    if color == 'orange':
        return 'orange'
    else:
        return 'apple'
    
for color in colors:
    print("If the fruit is", color, "I guess:", classify_fruit(color))
    

# Let's try a fruit of your choice!
your_color = input("Enter a fruit color (red, green, orange): ")
print("I guess:", classify_fruit(your_color))

# What happens if your input is not a color in our list?
mystery_color = input("Guess a mystery fruit color: ")
result = classify_fruit(mystery_color)
print("With mystery color, I guess:", result)

# Let's handle unknown colors in our classifier.
def classify_fruit_safe(color):
    if color == 'orange':
        return 'orange'
    elif color == 'red' or color == 'green':
        return 'apple'
    else:
        return 'unknown'
    
print("Test blue:", classify_fruit_safe('blue'))

# Let's use scikit-learn for simple regression.
from sklearn.linear_model import LinearRegression
import numpy as np

X = np.array(ages).reshape(-1, 1)
y = np.array(weights)

model = LinearRegression()
model.fit(X, y)

print("Predicting the weight for a 7-month-old kitten:", model.predict([[7]])[0], "grams")

# Let's use scikit-learn for simple classification.
from sklearn.tree import DecisionTreeClassifier

color_map = {'red':0, 'green':1, 'orange':2}
Xc = np.array([color_map[c] for c in colors]).reshape(-1,1)
yc = np.array([0 if l == 'apple' else 1 for l in labels])

clf = DecisionTreeClassifier()
clf.fit(Xc, yc)

test_color = color_map['orange']
predicted_label = clf.predict([[test_color]])[0]
if predicted_label == 1:
    print("Classifier predicts: orange")
else:
    print("Classifier predicts: apple")
    

# Here are some study data: hours vs. grades.
hours = [2, 4, 6, 8, 10]
grades = [55, 65, 78, 88, 96]

# Regression to guess a grade from study hours.
from sklearn.linear_model import LinearRegression
import numpy as np

Xh = np.array(hours).reshape(-1, 1)
yh = np.array(grades)

grade_model = LinearRegression()
grade_model.fit(Xh, yh)

new_hours = int(input("How many hours did you study? "))
predicted_grade = grade_model.predict([[new_hours]])[0]
print("Predicted exam grade:", round(predicted_grade, 1))

# Classify: Pass if grade 60 or higher, else Fail.
def pass_fail(grade):
    if grade >= 60:
        return 'PASS'
    else:
        return 'FAIL'
    
print("Prediction:", pass_fail(predicted_grade))

# List length mismatch: What happens if lists are different lengths?
bad_ages = [1,2,3]
bad_weights = [300,400]
try:
    for i in range(len(bad_ages)):
        print(bad_ages[i], bad_weights[i])
except IndexError:
    print("Oops! The lists do not match in length.")