quick-sentiments 0.4.3__tar.gz → 0.4.4__tar.gz

{quick_sentiments-0.4.3/quick_sentiments.egg-info → quick_sentiments-0.4.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: quick-sentiments
-Version: 0.4.3
+Version: 0.4.4
 Summary: Sentiment Analysis pipeline
 Author: Alabhya Dahal
 Author-email: Alabhya Dahal <alabhya.dahal@gmail.com>
@@ -12,9 +12,10 @@ Classifier: Intended Audience :: Science/Research
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: Text Processing :: Linguistic
@@ -37,12 +38,16 @@ Requires-Dist: twine; extra == "dev"
 Requires-Dist: build; extra == "dev"
 Provides-Extra: hf
 Requires-Dist: sentence-transformers>=2.2.0; extra == "hf"
+Provides-Extra: dl
+Requires-Dist: tensorflow>=2.13.0; extra == "dl"
+Requires-Dist: scikeras>=0.12.0; extra == "dl"
 Dynamic: author
 Dynamic: license-file
 
 [![PyPI Version](https://img.shields.io/pypi/v/quick-sentiments)](https://pypi.org/project/quick-sentiments/)
 [![PyPI Downloads](https://static.pepy.tech/badge/quick-sentiments)](https://pepy.tech/project/quick-sentiments)
 <img src="https://img.shields.io/badge/Python-3776AB?style=flat-square&logo=python&logoColor=white" />
+
 #  Quick Sentiments
 
 ## Updates
@@ -59,7 +64,7 @@ git clone https://github.com/AlabhyaMe/quick_sentiments.git
 Then run the command in the command prompt or notebook where git is cloned. Make sure you are in the main directory - quick_sentiments
 
 ```
-pip install .\dist\quick_sentiments-0.4.1-py3-none-any.whl # please note, sometimes I might not have updated the version number to the  latest
+pip install .\dist\quick_sentiments-0.4.3-py3-none-any.whl # please note, sometimes I might not have updated the version number to the  latest
 ```
 
 This Python package is designed to streamline natural language processing (NLP) for sentiment analysis. It achieves this by combining various vectorization techniques with machine learning models. The package automates the often complex and time-consuming vectorization process, allowing users to skip the manual coding typically required for this step. Additionally, users can easily select their preferred machine learning models to conduct sentiment analysis.
@@ -86,6 +91,7 @@ This Python package is designed to streamline natural language processing (NLP)
   - XGBoost
   - Naive Bayesian
   - Neural Network
+  - Naive Bayes
 - **Hyperparameter Tuning Support**:
   - All models are compatible with GridSearchCV.
   - By default, models run with standard parameters for quick testing.

{quick_sentiments-0.4.3 → quick_sentiments-0.4.4}/README.md

@@ -1,6 +1,7 @@
 [![PyPI Version](https://img.shields.io/pypi/v/quick-sentiments)](https://pypi.org/project/quick-sentiments/)
 [![PyPI Downloads](https://static.pepy.tech/badge/quick-sentiments)](https://pepy.tech/project/quick-sentiments)
 <img src="https://img.shields.io/badge/Python-3776AB?style=flat-square&logo=python&logoColor=white" />
+
 #  Quick Sentiments
 
 ## Updates
@@ -17,7 +18,7 @@ git clone https://github.com/AlabhyaMe/quick_sentiments.git
 Then run the command in the command prompt or notebook where git is cloned. Make sure you are in the main directory - quick_sentiments
 
 ```
-pip install .\dist\quick_sentiments-0.4.1-py3-none-any.whl # please note, sometimes I might not have updated the version number to the  latest
+pip install .\dist\quick_sentiments-0.4.3-py3-none-any.whl # please note, sometimes I might not have updated the version number to the  latest
 ```
 
 This Python package is designed to streamline natural language processing (NLP) for sentiment analysis. It achieves this by combining various vectorization techniques with machine learning models. The package automates the often complex and time-consuming vectorization process, allowing users to skip the manual coding typically required for this step. Additionally, users can easily select their preferred machine learning models to conduct sentiment analysis.
@@ -44,6 +45,7 @@ This Python package is designed to streamline natural language processing (NLP)
   - XGBoost
   - Naive Bayesian
   - Neural Network
+  - Naive Bayes
 - **Hyperparameter Tuning Support**:
   - All models are compatible with GridSearchCV.
   - By default, models run with standard parameters for quick testing.

{quick_sentiments-0.4.3 → quick_sentiments-0.4.4}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "quick-sentiments"
-version = "0.4.3" # change in prediction function
+version = "0.4.4" # tensorflow enters !
 authors = [
   { name="Alabhya Dahal", email="alabhya.dahal@gmail.com" },
 ]
@@ -20,9 +20,10 @@ classifiers = [
     "License :: OSI Approved :: MIT License",
     "Operating System :: OS Independent",
     "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.8",
-    "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
     "Topic :: Scientific/Engineering",
     "Topic :: Software Development :: Libraries :: Python Modules",
     "Topic :: Text Processing :: Linguistic"
@@ -54,6 +55,11 @@ hf = [
     "sentence-transformers>=2.2.0" # <--- NEW: Optional Hugging Face installation
 ]
 
+dl = [
+    "tensorflow>=2.13.0",     # 2.13+ is generally very stable with newer Python versions
+    "scikeras>=0.12.0",       # Required for the GridSearchCV wrapper we built
+]
+
 [tool.setuptools.packages.find]
 where = ["."]
 

quick_sentiments-0.4.4/quick_sentiments/ml_algo/ts_model.py

@@ -0,0 +1,92 @@
+# ml_algo/tf_model.py
+
+import numpy as np
+from scipy.sparse import issparse
+from sklearn.model_selection import GridSearchCV
+
+# 1. Gracefully handle the Optional Dependencies
+try:
+    import tensorflow as tf
+    from scikeras.wrappers import KerasClassifier
+except ImportError:
+    raise ImportError(
+        "TensorFlow or SciKeras is missing. "
+        "To use the deep learning models, please install the optional dependencies:\n"
+        "pip install quick_sentiments[dl]"
+    )
+
+def build_keras_model(input_dim, num_classes, hidden_units=128, dropout_rate=0.3):
+    """Builds the core TensorFlow architecture for SciKeras to use."""
+    model = tf.keras.Sequential([
+        tf.keras.layers.Input(shape=(input_dim,)),
+        tf.keras.layers.Dense(hidden_units, activation='relu'),
+        tf.keras.layers.Dropout(dropout_rate),
+        tf.keras.layers.Dense(int(hidden_units/2), activation='relu'),
+        tf.keras.layers.Dense(num_classes, activation='softmax')
+    ])
+    model.compile(
+        optimizer='adam',
+        loss='sparse_categorical_crossentropy',
+        metrics=['accuracy']
+    )
+    return model
+
+def train_and_predict(X_train, y_train, X_test, perform_tuning=False, random_state=42):
+    """
+    Trains a TensorFlow Neural Network seamlessly within the scikit-learn pipeline.
+    """
+    tf.random.set_seed(random_state)
+    
+    # Handle Sparse Data from Bag-of-Words / TF-IDF
+    if issparse(X_train):
+        print("   - Converting sparse text matrix to dense array for TensorFlow...")
+        X_train = X_train.toarray()
+        X_test = X_test.toarray()
+
+    input_dim = X_train.shape[1]
+    num_classes = len(np.unique(y_train))
+    print(f"   - Building TF Model: Input Features = {input_dim}, Output Classes = {num_classes}")
+    
+    # Wrap the Keras model so it acts exactly like your MLPClassifier
+    keras_estimator = KerasClassifier(
+        model=build_keras_model,
+        model__input_dim=input_dim,
+        model__num_classes=num_classes,
+        epochs=10,
+        batch_size=32,
+        verbose=0 
+    )
+
+    if perform_tuning:
+        print("   - Starting TensorFlow training with GridSearchCV for hyperparameter tuning...")
+        
+        param_grid = {
+            'model__hidden_units': [64, 128],
+            'model__dropout_rate': [0.2, 0.4],
+            'batch_size': [32, 64]
+        }
+        
+        grid_search = GridSearchCV(
+            estimator=keras_estimator,
+            param_grid=param_grid,
+            cv=3, 
+            scoring='accuracy',
+            n_jobs=-1,
+            verbose=1
+        )
+        
+        grid_search.fit(X_train, y_train)
+        best_model = grid_search.best_estimator_
+        print("\n   - Best Hyperparameters found:")
+        print(grid_search.best_params_)
+        
+    else:
+        print("   - Training TensorFlow model with default parameters...")
+        best_model = keras_estimator
+        # verbose=1 shows the progress bar when not tuning
+        best_model.fit(X_train, y_train, epochs=10, batch_size=32, verbose=1)
+
+    print("   - Generating predictions...")
+    y_pred = best_model.predict(X_test)
+
+    return y_pred, best_model

{quick_sentiments-0.4.3 → quick_sentiments-0.4.4}/quick_sentiments/pipeline.py

@@ -116,6 +116,13 @@ def run_pipeline(
         "xgboost": "XGB"
     }
 
+    MODEL_MAP = {
+        # ... your other models ...
+        "tf": "tf_model",
+        "tensorflow": "tf_model",
+        "keras": "tf_model"
+    }
+
     actual_vec_module = VEC_MAP.get(vectorizer_name.lower(), vectorizer_name)
     actual_model_module = MODEL_MAP.get(model_name.lower(), model_name)
 

{quick_sentiments-0.4.3 → quick_sentiments-0.4.4/quick_sentiments.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: quick-sentiments
-Version: 0.4.3
+Version: 0.4.4
 Summary: Sentiment Analysis pipeline
 Author: Alabhya Dahal
 Author-email: Alabhya Dahal <alabhya.dahal@gmail.com>
@@ -12,9 +12,10 @@ Classifier: Intended Audience :: Science/Research
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: Text Processing :: Linguistic
@@ -37,12 +38,16 @@ Requires-Dist: twine; extra == "dev"
 Requires-Dist: build; extra == "dev"
 Provides-Extra: hf
 Requires-Dist: sentence-transformers>=2.2.0; extra == "hf"
+Provides-Extra: dl
+Requires-Dist: tensorflow>=2.13.0; extra == "dl"
+Requires-Dist: scikeras>=0.12.0; extra == "dl"
 Dynamic: author
 Dynamic: license-file
 
 [![PyPI Version](https://img.shields.io/pypi/v/quick-sentiments)](https://pypi.org/project/quick-sentiments/)
 [![PyPI Downloads](https://static.pepy.tech/badge/quick-sentiments)](https://pepy.tech/project/quick-sentiments)
 <img src="https://img.shields.io/badge/Python-3776AB?style=flat-square&logo=python&logoColor=white" />
+
 #  Quick Sentiments
 
 ## Updates
@@ -59,7 +64,7 @@ git clone https://github.com/AlabhyaMe/quick_sentiments.git
 Then run the command in the command prompt or notebook where git is cloned. Make sure you are in the main directory - quick_sentiments
 
 ```
-pip install .\dist\quick_sentiments-0.4.1-py3-none-any.whl # please note, sometimes I might not have updated the version number to the  latest
+pip install .\dist\quick_sentiments-0.4.3-py3-none-any.whl # please note, sometimes I might not have updated the version number to the  latest
 ```
 
 This Python package is designed to streamline natural language processing (NLP) for sentiment analysis. It achieves this by combining various vectorization techniques with machine learning models. The package automates the often complex and time-consuming vectorization process, allowing users to skip the manual coding typically required for this step. Additionally, users can easily select their preferred machine learning models to conduct sentiment analysis.
@@ -86,6 +91,7 @@ This Python package is designed to streamline natural language processing (NLP)
   - XGBoost
   - Naive Bayesian
   - Neural Network
+  - Naive Bayes
 - **Hyperparameter Tuning Support**:
   - All models are compatible with GridSearchCV.
   - By default, models run with standard parameters for quick testing.

{quick_sentiments-0.4.3 → quick_sentiments-0.4.4}/quick_sentiments.egg-info/SOURCES.txt

@@ -19,6 +19,7 @@ quick_sentiments/ml_algo/logit.py
 quick_sentiments/ml_algo/nb.py
 quick_sentiments/ml_algo/nn.py
 quick_sentiments/ml_algo/rf.py
+quick_sentiments/ml_algo/ts_model.py
 quick_sentiments/vect/BOW.py
 quick_sentiments/vect/__init__.py
 quick_sentiments/vect/glove_100.py

{quick_sentiments-0.4.3 → quick_sentiments-0.4.4}/quick_sentiments.egg-info/requires.txt

@@ -14,5 +14,9 @@ black>=22.0
 twine
 build
 
+[dl]
+tensorflow>=2.13.0
+scikeras>=0.12.0
+
 [hf]
 sentence-transformers>=2.2.0