"""Train and evaluate a Keras Embedding sentiment model on IMDb.
Run: python keras_embedding_imdb.py
Install: pip install tensorflow keras numpy scikit-learn matplotlib
Keras downloads its integer-tokenized IMDb dataset on first run.
"""
import matplotlib
matplotlib.use("Agg")
import matplotlib.pyplot as plt
import numpy as np
import keras
from keras import layers
from keras.datasets import imdb
from keras.utils import pad_sequences
from sklearn.metrics import (ConfusionMatrixDisplay, classification_report,
                             confusion_matrix, roc_auc_score)
from sklearn.model_selection import train_test_split

SEED = 42
VOCAB = 12000
LENGTH = 220
keras.utils.set_random_seed(SEED)

# IMDb ships as token IDs; 0 is padding, 1 is start, 2 is OOV.
(train_sequences, train_labels), (test_sequences, test_labels) = imdb.load_data(
    num_words=VOCAB, seed=SEED)
X_all = pad_sequences(train_sequences, maxlen=LENGTH, padding="post",
                      truncating="pre")
X_test = pad_sequences(test_sequences, maxlen=LENGTH, padding="post",
                       truncating="pre")
y_all = np.asarray(train_labels, dtype="int32")
y_test = np.asarray(test_labels, dtype="int32")

# Split only the official training partition; keep the official test untouched.
train_ids, val_ids = train_test_split(
    np.arange(len(X_all)), test_size=0.2, random_state=SEED,
    stratify=y_all)
X_train, y_train = X_all[train_ids], y_all[train_ids]
X_val, y_val = X_all[val_ids], y_all[val_ids]
print("train / validation / test:", len(X_train), len(X_val), len(X_test))

model = keras.Sequential([
    keras.Input(shape=(LENGTH,), dtype="int32"),
    layers.Embedding(input_dim=VOCAB, output_dim=64, mask_zero=True,
                     name="learned_word_vectors"),
    layers.GlobalAveragePooling1D(),
    layers.Dense(64, activation="relu"),
    layers.Dropout(0.3),
    layers.Dense(1, activation="sigmoid"),
])
model.compile(optimizer=keras.optimizers.Adam(1e-3),
              loss="binary_crossentropy",
              metrics=[keras.metrics.BinaryAccuracy(name="accuracy"),
                       keras.metrics.AUC(name="auc")])
model.summary()
model.fit(X_train, y_train, validation_data=(X_val, y_val),
          batch_size=128, epochs=15, verbose=2,
          callbacks=[keras.callbacks.EarlyStopping(
              monitor="val_loss", patience=2, restore_best_weights=True)])
print("Untouched test metrics:", model.evaluate(X_test, y_test,
                                                return_dict=True, verbose=0))

probabilities = model.predict(X_test, batch_size=256, verbose=0).ravel()
predictions = (probabilities >= 0.5).astype("int32")
print(classification_report(y_test, predictions,
                            target_names=["negative", "positive"],
                            zero_division=0))
print("Test ROC AUC:", round(roc_auc_score(y_test, probabilities), 4))
cm = confusion_matrix(y_test, predictions, labels=[0, 1])
ConfusionMatrixDisplay(cm, display_labels=["negative", "positive"]).plot(
    cmap="Blues", colorbar=False)
plt.title("IMDb held-out test · Keras Embedding")
plt.tight_layout()
plt.savefig("embedding_imdb_confusion.png", dpi=160)
plt.close()

# Inspect learned rows after training; ID 0 is the padding row.
weights = model.get_layer("learned_word_vectors").get_weights()[0]
print("Embedding matrix:", weights.shape)
print("Example learned vector for token ID 10:", np.round(weights[10, :8], 3))
print("First 5 test probabilities:", np.round(probabilities[:5], 3))
model.save("embedding_imdb.keras")
print("Saved embedding_imdb.keras and embedding_imdb_confusion.png")
