# Always import the warnings library to filter out warnings
import warnings
warnings.filterwarnings("ignore")  # This line hides most warning messages

# Let us look at some numbers that need scaling
ages = [10, 18, 35, 45, 60]
salaries = [15000, 25000, 45000, 60000, 90000]
print("Ages:", ages)
print("Salaries:", salaries)

# Data setup: Let us load the Titanic dataset
import pandas as pd
url = "https://raw.githubusercontent.com/datasciencedojo/datasets/master/titanic.csv"
df = pd.read_csv(url)
print("Data shape:", df.shape)
df.head()

# Let us check what columns we have and see the target variable distribution
print("Columns:", df.columns.tolist())
print(df['Survived'].value_counts())

# Let us focus on numerical columns for scaling
num_cols = ['Age', 'Fare']
df_num = df[num_cols]
df_num.head()

# Standard scaling: zero mean, unit variance
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
df_scaled = scaler.fit_transform(df_num)
print(df_scaled[:5])

# Min-Max scaling example: scaling to range 0-1
from sklearn.preprocessing import MinMaxScaler
minmax_scaler = MinMaxScaler()
df_minmax = minmax_scaler.fit_transform(df_num)
print(df_minmax[:5])

# Separate our features (X) and label (y)
from sklearn.model_selection import train_test_split
X = df[['Age', 'Fare']].values
y = df['Survived'].values
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=42)
print('Train shape:', X_train.shape, 'Test shape:', X_test.shape)

# Build a pipeline: scale then fit logistic regression
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.linear_model import LogisticRegression
pipe = Pipeline([
    ("imputer", SimpleImputer(strategy="mean")),
    ("scaler", StandardScaler()),
    ("model", LogisticRegression(random_state=42))
])
pipe.fit(X_train, y_train)
score = pipe.score(X_test, y_test)
print("Test accuracy:", round(score, 2))

# Modify pipeline to use MinMaxScaler instead
pipe2 = Pipeline([
    ("imputer", SimpleImputer(strategy="mean")),
    ("scaler", MinMaxScaler()),
    ("model", LogisticRegression(random_state=42))
])
pipe2.fit(X_train, y_train)
score2 = pipe2.score(X_test, y_test)
print("Test accuracy with MinMaxScaler:", round(score2, 2))

# Add a missing value imputer to pipeline
from sklearn.impute import SimpleImputer
pipe3 = Pipeline([
    ("imputer", SimpleImputer(strategy="mean")),
    ("scaler", StandardScaler()),
    ("model", LogisticRegression(random_state=42))
])
pipe3.fit(X_train, y_train)
score3 = pipe3.score(X_test, y_test)
print("Test accuracy with imputer:", round(score3, 2))

# Check if there are any missing values in Age or Fare
print("Missing Age:", df['Age'].isnull().sum())
print("Missing Fare:", df['Fare'].isnull().sum())

# Practice: let us build a pipeline for a different model (KNeighborsClassifier)
from sklearn.neighbors import KNeighborsClassifier
pipe_knn = Pipeline([
    ("imputer", SimpleImputer(strategy="mean")),
    ("scaler", StandardScaler()),
    ("model", KNeighborsClassifier())
])
pipe_knn.fit(X_train, y_train)
score_knn = pipe_knn.score(X_test, y_test)
print("Test accuracy for k-NN:", round(score_knn, 2))

# Challenge: Try your own input! Enter age and fare to predict survival
age = float(input("Passenger Age: "))
fare = float(input("Ticket Fare: "))
prediction = pipe.predict([[age, fare]])
print("Predicted survival (0=No, 1=Yes):", prediction[0])