Upload models.py

models.py

@@ -0,0 +1,119 @@
+import pandas as pd
+import numpy as np
+from sklearn.naive_bayes import MultinomialNB, ComplementNB
+from sklearn.linear_model import LogisticRegression
+from sklearn.svm import LinearSVC
+from sklearn.calibration import CalibratedClassifierCV
+from sklearn.ensemble import (
+    VotingClassifier, RandomForestClassifier, StackingClassifier,
+    GradientBoostingClassifier, HistGradientBoostingClassifier
+)
+from sklearn.feature_selection import SelectKBest, f_classif
+from sklearn.pipeline import Pipeline
+from sklearn.compose import ColumnTransformer
+from sklearn.preprocessing import MinMaxScaler
+from sklearn.feature_extraction.text import TfidfVectorizer
+from dl_model import DeepNewsClassifier  # §3.3.2 Deep Learning Module
+
+
+class FakeNewsModels:
+    def __init__(self):
+        # All hand-crafted numeric columns (original + new deception features)
+        num_cols = [
+            # Original features
+            'lexical_density', 'capital_ratio', 'noun_ratio', 'speaker_reliability',
+            'sentiment_score', 'complexity_score', 'subjectivity_score',
+            'verb_ratio', 'adj_ratio', 'adv_ratio', 'punctuation_aggression',
+            'entity_density', 'formal_cadence', 'official_marker',
+            # Hedging & Certainty
+            'hedge_ratio', 'certainty_ratio', 'hedge_certainty_diff',
+            # Emotional
+            'emotional_intensity', 'sentiment_extremity',
+            'negativity_score', 'positivity_score',
+            # Numerical
+            'number_density', 'has_percentage', 'has_dollar_amount', 'number_count',
+            # Source / Attribution
+            'attribution_ratio', 'has_source_citation',
+            # Readability
+            'ari_score', 'gunning_fog', 'avg_sentence_length',
+            # Pronoun & Modality
+            'first_person_ratio', 'modal_ratio', 'negation_ratio',
+            # Comparison
+            'comparative_ratio', 'superlative_ratio',
+            # Voice
+            'passive_ratio',
+            # Urgency / Style
+            'caps_word_ratio', 'ellipsis_count',
+            'exclamation_marks', 'question_marks', 'quotes_count',
+            'total_words', 'avg_word_length',
+            # Social context history
+            'false_history_ratio', 'true_history_ratio', 'history_volume',
+            'is_republican', 'is_democrat',
+        ]
+
+        preprocessor = ColumnTransformer(
+            transformers=[
+                ('text', TfidfVectorizer(
+                    ngram_range=(1, 3),
+                    max_features=12000,
+                    min_df=3,
+                    max_df=0.75,
+                    sublinear_tf=True,
+                    stop_words='english'
+                ), 'statement'),
+                ('meta', MinMaxScaler(), num_cols),
+            ],
+            remainder='drop'
+        )
+
+        # Feature selection: keep top 5000 features
+        selector = SelectKBest(f_classif, k=5000)
+
+        # Individual classifiers — tuned for better performance and calibrated uncertainty
+        nb_clf = CalibratedClassifierCV(ComplementNB(alpha=0.1))
+        lr_clf = LogisticRegression(
+            C=0.8, max_iter=3000, solver='lbfgs',
+            class_weight='balanced', l1_ratio=0
+        )
+        svm_clf = CalibratedClassifierCV(
+            LinearSVC(C=0.5, max_iter=5000, class_weight='balanced', dual='auto')
+        )
+        rf_clf = CalibratedClassifierCV(
+            RandomForestClassifier(
+                n_estimators=600, max_depth=22, min_samples_leaf=3,
+                class_weight='balanced', random_state=42, n_jobs=-1
+            )
+        )
+
+        self.models = {
+            'nb':  Pipeline([('pre', preprocessor), ('sel', selector), ('clf', nb_clf)]),
+            'lr':  Pipeline([('pre', preprocessor), ('sel', selector), ('clf', lr_clf)]),
+            'svm': Pipeline([('pre', preprocessor), ('sel', selector), ('clf', svm_clf)]),
+            'rf':  Pipeline([('pre', preprocessor), ('sel', selector), ('clf', rf_clf)]),
+            # §3.3.2 Deep Learning Module — BiLSTM-approximating dual encoder
+            'dl':  DeepNewsClassifier(),
+        }
+
+        # STACKING ENSEMBLE with LogisticRegression meta-learner (§3.3)
+        # Includes Deep Learning module as 5th base estimator
+        self.models['ensemble'] = StackingClassifier(
+            estimators=[
+                ('nb',  self.models['nb']),
+                ('lr',  self.models['lr']),
+                ('svm', self.models['svm']),
+                ('rf',  self.models['rf']),
+                ('dl',  self.models['dl']),  # §3.3.2
+            ],
+            final_estimator=LogisticRegression(
+                C=0.5, class_weight='balanced', max_iter=1000
+            ),
+            stack_method='predict_proba',
+            cv=5,
+            n_jobs=-1
+        )
+
+    def get_model(self, name):
+        return self.models.get(name)
+
+    def get_all_models(self):
+        return self.models