New training with new data & new release

adamspd · May 4, 2024 · b417ad4 · b417ad4
1 parent 3161949
commit b417ad4
Show file tree

Hide file tree

Showing 14 changed files with 10,284 additions and 6 deletions.
diff --git a/requirements.txt b/requirements.txt
@@ -1,10 +1,10 @@
 scikit-learn==1.4.2
 imbalanced-learn==0.12.2
-pandas==2.2.1
+pandas==2.2.2
 nltk~=3.8.1
-setuptools==69.2.0
-pytest==8.1.1
+setuptools==69.5.1
+pytest==8.2.0
 requests~=2.31.0
 imblearn~=0.0
-joblib~=1.4.0
+joblib~=1.4.2
 xgboost~=2.0.3
diff --git a/spam_detector_ai/__init__.py b/spam_detector_ai/__init__.py
@@ -4,5 +4,5 @@
 __description__ = "A package for detecting and filtering spam messages using Machine Learning models."
 __package_name__ = "spam-detector-ai"
 __url__ = "https://github.com/adamspd/spam-detection-project"
-__version__ = "2.1.13"
+__version__ = "2.1.14"
 __test_version__ = False
diff --git a/spam_detector_ai/data/spam.csv b/spam_detector_ai/data/spam.csv
diff --git a/spam_detector_ai/models/bayes/naive_bayes_model.joblib b/spam_detector_ai/models/bayes/naive_bayes_model.joblib
diff --git a/spam_detector_ai/models/bayes/naive_bayes_vectoriser.joblib b/spam_detector_ai/models/bayes/naive_bayes_vectoriser.joblib
diff --git a/spam_detector_ai/models/logistic_regression/logistic_regression_model.joblib b/spam_detector_ai/models/logistic_regression/logistic_regression_model.joblib
diff --git a/spam_detector_ai/models/logistic_regression/logistic_regression_vectoriser.joblib b/spam_detector_ai/models/logistic_regression/logistic_regression_vectoriser.joblib
diff --git a/spam_detector_ai/models/random_forest/random_forest_model.joblib b/spam_detector_ai/models/random_forest/random_forest_model.joblib
diff --git a/spam_detector_ai/models/random_forest/random_forest_vectoriser.joblib b/spam_detector_ai/models/random_forest/random_forest_vectoriser.joblib
diff --git a/spam_detector_ai/models/svm/svm_model.joblib b/spam_detector_ai/models/svm/svm_model.joblib
diff --git a/spam_detector_ai/models/svm/svm_vectoriser.joblib b/spam_detector_ai/models/svm/svm_vectoriser.joblib
diff --git a/spam_detector_ai/models/xgb/xgb_model.joblib b/spam_detector_ai/models/xgb/xgb_model.joblib
diff --git a/spam_detector_ai/models/xgb/xgb_vectoriser.joblib b/spam_detector_ai/models/xgb/xgb_vectoriser.joblib
diff --git a/spam_detector_ai/tests/test.py b/spam_detector_ai/tests/test.py
@@ -1,6 +1,7 @@
 # spam_detector_ai/test_and_tuning/test.py
 
 import os
+import sys
 
 from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
 from sklearn.model_selection import train_test_split
@@ -10,6 +11,8 @@
 from spam_detector_ai.prediction.predict import SpamDetector
 from spam_detector_ai.training.train_models import ModelTrainer
 
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '..', '..')))
+
 
 class TestModel:
     def __init__(self):
@@ -20,7 +23,7 @@ def __init__(self):
         # Assuming the spam_detector_ai directory is one level up from the current directory
         base_dir = os.path.dirname(current_dir)
         data_path = os.path.join(base_dir, 'data/spam.csv')
-        self.initial_trainer = ModelTrainer(data_path=data_path, classifier_type=None, logger=self.logger)
+        self.initial_trainer = ModelTrainer(data_path=data_path, logger=self.logger)
         self.processed_data = self.initial_trainer.preprocess_data_()
 
         # Split the data once