Add test_team.py

test_team.py

@@ -0,0 +1,70 @@
+# train.py
+
+import pandas as pd
+import joblib
+import numpy as np
+from sklearn.linear_model import LogisticRegression
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.multiclass import OneVsRestClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import f1_score
+
+LABELS = ['admiration','anger','disgust','fear','hope','joy','love','pride','sadness']
+
+def to_binary(label_string):
+    present = [e.strip() for e in str(label_string).split(',')]
+    return [1 if label in present else 0 for label in LABELS]
+
+# ── load ──────────────────────────────────────────────────────────
+print("Loading dataset...")
+df = pd.read_excel("Multi-Labeled_Emotions_Modified.xlsx")
+df = df[['Tweets (text)', 'Emotions (Multi-labeled)']].dropna()
+print(f"Total rows: {len(df)}")
+
+X = df['Tweets (text)'].tolist()
+y = [to_binary(row) for row in df['Emotions (Multi-labeled)']]
+
+# ── split ─────────────────────────────────────────────────────────
+X_train, X_test, y_train, y_test = train_test_split(
+    X, y, test_size=0.2, random_state=42
+)
+print(f"Train: {len(X_train)} rows")
+print(f"Test:  {len(X_test)} rows")
+
+# ── save test set as hidden test data ─────────────────────────────
+test_emotions = [
+    ', '.join([LABELS[i] for i, val in enumerate(row) if val == 1])
+    for row in y_test
+]
+test_df = pd.DataFrame({
+    'Tweets (text)': X_test,
+    'Emotions (Multi-labeled)': test_emotions
+})
+test_df.to_excel("test_set.xlsx", index=False)
+print("Saved test_set.xlsx")
+
+# ── train ─────────────────────────────────────────────────────────
+print("Training...")
+vectorizer = TfidfVectorizer(max_features=10000, ngram_range=(1,2))
+X_train_tfidf = vectorizer.fit_transform(X_train)
+X_test_tfidf  = vectorizer.transform(X_test)
+
+classifier = OneVsRestClassifier(
+    LogisticRegression(max_iter=1000, C=1.0)
+)
+classifier.fit(X_train_tfidf, np.array(y_train))
+print("Training done.")
+
+# ── quick check ───────────────────────────────────────────────────
+y_pred = classifier.predict(X_test_tfidf)
+f1 = f1_score(np.array(y_test), y_pred, average='macro', zero_division=0)
+print(f"F1 score: {f1:.4f}")
+
+# ── save ──────────────────────────────────────────────────────────
+model_bundle = {
+    "vectorizer": vectorizer,
+    "classifier": classifier,
+    "labels": LABELS
+}
+joblib.dump(model_bundle, "model.pkl")
+print("Saved model.pkl")