from google.colab import drive
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.decomposition import PCA
from sklearn.cluster import KMeans
from sklearn.preprocessing import StandardScaler
import warnings

drive.mount('/content/gdrive')
df = pd.read_csv('/content/gdrive/My Drive/datasets/penguins.csv')
df = df.dropna()
df = df.drop([9, 14])

# Inspect the results
df.head()

df.body_mass_g.hist()

from sklearn.model_selection import train_test_split

# Create train/test split (20% test)
df_train, df_test = train_test_split(df, test_size=0.2, random_state=42)

print(f"Training set size: {len(df_train)}")
print(f"Test set size: {len(df_test)}")

# One-hot encode training data
df_train = pd.get_dummies(df_train).drop("sex_.", axis=1, errors="ignore")

# One-hot encode test data
df_test = pd.get_dummies(df_test).drop("sex_.", axis=1, errors="ignore")

df_train

scaler = StandardScaler()

# Fit scaler on training data and transform
X_train = pd.DataFrame(
    scaler.fit_transform(df_train),
    columns=df_train.columns,
    index=df_train.index
)

# Transform test data using the fitted scaler
X_test = pd.DataFrame(
    scaler.transform(df_test),
    columns=df_test.columns,
    index=df_test.index
)

X_test.plot(kind="scatter", x="culmen_length_mm", y="body_mass_g")

# First, determine optimal number of components using training data
pca = PCA(n_components=None)
pca_temp = pca.fit(X_train)
n_components = sum(pca_temp.explained_variance_ratio_ > 0.1)
print(f"Number of components with variance > 0.1: {n_components}")

# Now fit PCA with optimal components
pca = PCA(n_components=n_components)
X_train = pd.DataFrame(
    pca.fit_transform(X_train),
    index=X_train.index
)

# Transform test data
X_test = pd.DataFrame(
    pca.transform(X_test),
    index=X_test.index
)

X_test


X_test.plot(kind="scatter", x=0, y=1)

inertia = []
for k in range(1, 10):
    kmeans = KMeans(n_clusters=k, random_state=42).fit(X_train)
    inertia.append(kmeans.inertia_)

plt.plot(range(1, 10), inertia, marker="o")
plt.xlabel("Number of clusters")
plt.ylabel("Inertia")
plt.title("Elbow Method")
plt.show()


n_clusters = 4


# Fit K-means on training data
kmeans = KMeans(n_clusters=n_clusters, random_state=42).fit(X_train)

# Get cluster assignments for training data
train_clusters = kmeans.labels_

# Visualize the training clusters on the first two principal components
plt.scatter(X_train.iloc[:, 0], X_train.iloc[:, 1], c=train_clusters, cmap="viridis")
plt.xlabel("First Principal Component")
plt.ylabel("Second Principal Component")
plt.title(f"K-means Clustering on Training Data (K={n_clusters})")
plt.show()




# Predict clusters for test data
y_pred = kmeans.predict(X_test)

# Show cluster distribution in test set
print("Test set cluster distribution:")
print(pd.Series(y_pred).value_counts().sort_index())

# Visualize test set predictions
plt.figure(figsize=(12, 5))

# Plot training data
plt.subplot(1, 2, 1)
plt.scatter(X_train.iloc[:, 0], X_train.iloc[:, 1], c=train_clusters, cmap="viridis", alpha=0.6)
plt.xlabel("First Principal Component")
plt.ylabel("Second Principal Component")
plt.title(f"Training Data Clusters (K={n_clusters})")

# Plot test data
plt.subplot(1, 2, 2)
plt.scatter(X_test.iloc[:, 0], X_test.iloc[:, 1], c=y_pred, cmap="viridis", alpha=0.6)
plt.xlabel("First Principal Component")
plt.ylabel("Second Principal Component")
plt.title(f"Test Data Predictions")

plt.tight_layout()
plt.show()

# This clustering could be useful for:
# - Identifying different penguin subgroups for conservation efforts
# - Understanding natural groupings in the population
# - Feature engineering for supervised learning tasks
print("\nClustering complete! These groups could represent different penguin subpopulations or behavioral patterns.")