JustDataML 0.0.26__py3-none-any.whl

JDML/source/components/Model_Trainer.py

@@ -0,0 +1,103 @@
+import os
+import sys
+from dataclasses import dataclass
+
+from sklearn.metrics import r2_score, accuracy_score
+
+
+from ...source.Logger import logging
+from ...source.Utils import save_object, evaluate_model
+from ...source.Exception import CustomException
+
+
+
+
+@dataclass 
+class ModelTrainerConfig:
+
+    """
+    Creating a Model Trainer Config to store model inot a pickle file
+
+    """
+
+    train_model_file_path = os.path.join("artifact","model.pkl")
+
+class ModelTrainer:
+
+    """
+    Here we are Running the Models and Doing Evalution 
+    It will train based on the Problem Objective (Regression or Classification) 
+    If you have given Hyperparameter Argument as Yes it will do Hyperparater too for these Models 
+    I have tried to include all most frequently used models for both objectives.
+    This Function will pick up the best Models and train on that model with best hyper parameter tuning.
+    """
+
+    def __init__(self, models, hyperparameter_yes_or_no, problem_objective):
+        self.Models = models
+        self.HyperParamter_Yes_or_No = hyperparameter_yes_or_no
+        self.Problem_Objective = problem_objective
+        self.model_trainer_config = ModelTrainerConfig()
+
+    def initiate_model_trainer(self,train_array,test_array):
+        try:
+            logging.info("Splitting Training and Test input Data into Features and Target")
+            X_train,y_train,X_test,y_test = (
+                train_array[:,:-1],
+                train_array[:,-1],
+                test_array[:,:-1],
+                test_array[:,-1]
+            )
+
+            models = self.Models
+            logging.info(f"It will use {list(models.keys())} Models for Training ")
+            Hyparams= self.HyperParamter_Yes_or_No
+            logging.info(f" Models are Running with HypterParater Configuration of [{Hyparams}]")
+
+            model_report:dict = evaluate_model(X_train=X_train,y_train=y_train,
+                                               X_test=X_test,y_test=y_test,
+                                               models= models,param = Hyparams,prob = self.Problem_Objective)
+
+            #print(model_report)
+            ## to get the best score from the model
+            best_model_score = max(sorted(model_report.values()))
+                        
+            ## to get the best model name  from dict
+            best_model_name = list(model_report.keys())[
+                list(model_report.values()).index(best_model_score)
+            ]
+
+            best_model = models[best_model_name]
+            
+
+            if (best_model_score < 0.8) and (best_model_score >= 0.5):
+                #raise CustomException("No Best model Found need improvment",sys)
+                logging.info(f'Note : Need Improvement \n The best model is {best_model_name} with score {best_model_score}')
+            elif best_model_score < 0.5:
+                #raise CustomException("Something is Wrong please check with Data ? Features and codes",sys)
+                logging.info(f" There is Some ERROR in your model or Code please check Data,Features and Codes \n The best model is {best_model_name} with score {best_model_score} ")
+            else:
+                print(f"The Best model is {best_model_name} with score of {best_model_score}")
+
+            logging.info(f"Model is Trained and output is there \n The Best model is {best_model_name} with score of {best_model_score}")
+
+            save_object(
+                file_path=self.model_trainer_config.train_model_file_path,
+                obj=best_model
+            )
+
+            predicted = best_model.predict(X_test)
+
+            if self.Problem_Objective == 'Regression':
+                matric = r2_score(y_test,predicted)
+            elif self.Problem_Objective == 'Classification':
+                matric = accuracy_score(y_test,predicted)
+            else:
+                print("Correct Problem Objective")
+
+
+            #print(f"The best Score is {r2_sq}")
+            return matric
+
+
+        except Exception as e:
+            raise CustomException(e,sys)

JustDataML-0.0.26.dist-info/METADATA

@@ -0,0 +1,266 @@
+Metadata-Version: 2.1
+Name: JustDataML
+Version: 0.0.26
+Summary: This is a Machine Learning Tool Developed to Help Non Tech Students and Non Coders to try ML for there Data
+Home-page: https://github.com/jaideepsinhdabhi/JustDataML
+Author: Jaideepsinh Dabhi
+Author-email: jadieep.dabhi7603@gmail.com
+License: Apache License 2.0
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Operating System :: OS Independent
+Description-Content-Type: text/markdown
+Requires-Dist: pandas
+Requires-Dist: numpy
+Requires-Dist: seaborn
+Requires-Dist: matplotlib
+Requires-Dist: scikit-learn
+Requires-Dist: xgboost
+Requires-Dist: setuptools
+
+
+# JustDataML :Simplified Machine Learning for Everyone
+
+Welcome to JustDataML, a user-friendly tool designed to make machine learning accessible to all, regardless of technical background. JustDataML automates the process of model selection, data preprocessing, and prediction, allowing you to focus on insights rather than coding complexities.
+
+
+## Authors
+
+- [@jaideepsinhdabhi](https://www.github.com/jaideepsinhdabhi)
+
+
+## Features
+
+- Automated Model Selection
+- Streamlined Preprocessing
+- Quick Predictions
+- Flexible Configuration
+- Hyperparameter Tuning
+- Prediction accurately
+
+## Requirements
+
+to Run this Tool you will Require
+Below this thing to do
+
+
+## Installation
+
+Suggestion: Please Use a Virtual env for this to succesfully run it 
+
+1. Install my Application with pip install
+
+```bash
+  pip install JustDataML
+
+```
+   and Now you can use it as 
+
+```bash
+   JDML --Config <Data Config file> --Train --Predict <test.csv> --Output <Output Name>
+
+```
+
+2. Install by cloning this repository
+
+```bash
+  git clone https://github.com/jaideepsinhdabhi/JustDataML.git
+```
+Go into the Repo Folder
+
+```bash
+  cd JustDataML
+```
+we need to download all the required packages
+```bash
+  pip install -r requirements.txt
+```
+## Usage/Examples CLI Tool
+
+```bash
+python JDML/JDML.py -- Config <Data Config File> --Train --Predict <test.csv> --Output <Output Name>
+
+```
+### Arguments
+- `-C, --Config`: [Compulsory] You need to provide a configuration file to obtain all the necessary arguments.
+
+    Note: Make sure you give proper argument mentioned in the Document.
+
+- `-T, --Train`: [Optional] If provided, it initiates model training based on the specified data_config file. 
+
+    Note : Ensure that the Data files are available in the "Data" folder.
+
+- `-P, --Predict`: [Optional] If provided, performs prediction using the trained model. Make sure not to delete or modify the artifact folder to get the results.
+
+- `-O, --Output`: [Required with -P (--Predict)] Specifies the output name for the predicted dataframe generated from the test data.
+    Note: it will also generate Model_summary file and if Hyperparameter is given Yes in Config file then it will generate stats file for that too
+
+
+
+## Usage/Examples Python
+
+we can also use this tool as a python library
+```python
+from JDML.JDML import Just_Data_ML
+import argparse
+
+```
+Import the Tool
+
+```python
+
+arguments = argparse.Namespace(Config="Data_Config.csv",Train=True,Predict="Test.csv", Output="Output.csv")
+```
+Yes we need to give arguments like this (will fix thsi issue in next release)
+
+```python
+jdml=Just_Data_ML(arguments)
+
+```
+parsing the arugments
+
+```python
+jdml.Data_df
+```
+For checking the DataFrame you provided 
+
+```python
+jdml.Data_train()
+```
+For Model Training 
+
+```python
+jdml.Predict_test()
+
+```
+For Predicting the Test gvien
+
+Voila You will have the Prediction file (Column `Target_Out`) in the Output Folder.
+
+## Data Configuration File Example
+
+This is an example of a data configuration file (`Data_Config.csv`) used with the JustData_ML (JDML) tool. This file specifies the necessary information for training and predicting with machine learning models.
+
+### CSV Structure:
+
+The CSV file contains the following fields:
+
+- **Data_Name:** Name of the dataset file with extension and it should be present in Data Folder (`Iris.data` in this example).
+- **Features_Cols:** Comma-separated list of feature columns in the dataset (`sepal length, sepal width, petal length, petal width` in this example).
+- **Target_Col:** Name of the target column in the dataset (`class` in this example).
+- **Problem_Objective:** Objective of the machine learning task (`Classification` or `Regression`).
+- **Normalization_tech:** Normalization technique to be applied (`StandardScaler`, `MinMaxScaler`, etc.).
+- **Model_to_include:** Models to include in the training process (`ALL` or specific models). (below Listed for Models)
+- **HyperParamter_Yes_or_No:** Indicates whether hyperparameter tuning should be performed (`Yes` or `No`).
+
+
+    #####   A sample csv file and some Data are there in Data Folder for a demo Run
+
+    #### Note : It will also generate logs into a logs folder for every run please check for every Run to get more idea on that.
+
+## Available Models for Regression and Classification
+
+### Regression Models:
+
+1. **Random Forest**
+   - Description: Random Forest is an ensemble learning method that operates by constructing multiple decision trees during training and outputting the mean prediction of the individual trees.
+
+2. **Decision Tree**
+   - Description: Decision Tree is a non-parametric supervised learning method used for classification and regression. It works by partitioning the input space into regions and predicting the target variable based on the average of the training instances in the corresponding region.
+
+3. **Gradient Boosting**
+   - Description: Gradient Boosting is a machine learning technique for regression and classification problems that builds models in a stage-wise manner and tries to fit new models to the residuals of the previous models.
+
+4. **Linear Regression**
+   - Description: Linear Regression is a linear approach to modeling the relationship between a dependent variable and one or more independent variables.
+
+5. **XGBRegressor**
+   - Description: XGBoost is an optimized distributed gradient boosting library designed to be highly efficient, flexible, and portable.
+
+6. **Support Vector Reg**
+   - Description: Support Vector Regression (SVR) is a type of Support Vector Machine (SVM) algorithm that is used to predict a continuous variable.
+
+7. **Linear Ridge**
+   - Description: Ridge Regression is a linear regression technique that is used to analyze multiple regression data that suffer from multicollinearity.
+
+8. **Linear Lasso**
+   - Description: Lasso regression is a type of linear regression that uses shrinkage. It penalizes the absolute size of the regression coefficients.
+
+9. **ElasticNet**
+   - Description: ElasticNet is a linear regression model that combines the properties of Ridge Regression and Lasso Regression.
+
+10. **AdaBoost Regressor**
+    - Description: AdaBoost (Adaptive Boosting) is an ensemble learning method that combines multiple weak learners to create a strong learner.
+
+11. **KNeighborsRegressor**
+    - Description: KNeighborsRegressor is a simple, non-parametric method used for regression tasks based on the k-nearest neighbors algorithm.
+
+### Classification Models:
+
+1. **Logistic Regression**
+   - Description: Logistic Regression is a statistical method for analyzing a dataset in which there are one or more independent variables that determine an outcome.
+
+2. **Ridge Classification**
+   - Description: Ridge Classifier is a classifier that uses Ridge Regression to classify data points.
+
+3. **GaussianNB**
+   - Description: Gaussian Naive Bayes is a simple probabilistic classifier based on applying Bayes' theorem with strong independence assumptions between the features.
+
+4. **KNeighborsClassifier**
+   - Description: KNeighborsClassifier is a simple, instance-based learning algorithm used for classification tasks based on the k-nearest neighbors algorithm.
+
+5. **Decision Tree Classifier**
+   - Description: Decision Tree Classifier is a non-parametric supervised learning method used for classification.
+
+6. **Random Forest Classifier**
+   - Description: Random Forest Classifier is an ensemble learning method for classification that operates by constructing multiple decision trees during training and outputting the class that is the mode of the classes (classification) of the individual trees.
+
+7. **Support Vector Classifier**
+   - Description: Support Vector Classifier (SVC) is a type of Support Vector Machine (SVM) algorithm that is used for classification tasks.
+
+8. **AdaBoost Classifier**
+   - Description: AdaBoost Classifier is an ensemble learning method that combines multiple weak learners to create a strong learner.
+
+9. **Gradient Boosting Classifier**
+   - Description: Gradient Boosting Classifier is a machine learning technique for classification problems that builds models in a stage-wise manner and tries to fit new models to the residuals of the previous models.
+
+10. **XGBClassifier**
+    - Description: XGBoost Classifier is an optimized distributed gradient boosting library designed for classification problems.
+
+These are the available regression and classification models supported by the JDML tool. You can use them for training and prediction based on your specific machine learning tasks.
+
+## Feedback
+
+If you have any feedback or suggestions , please reach out to us at jaideep.dabhi7603@gmail.com
+
+
+## Acknowledgements
+
+ - [Krish Naik Playlist of End-to-End Machine Learning Project](https://youtube.com/playlist?list=PLZoTAELRMXVPS-dOaVbAux22vzqdgoGhG&si=Q1cXWDAZIdeeiC3m) This playlist really helped a lot I followed till the end and tried to code at the same time. 
+
+
+ - [Krish Naik Github Repo for Above Project ](https://github.com/krishnaik06/mlproject) Github Repo from the playlist for reference. 
+ - [How to Build a Complete Python Package Step-by-Step by ArjanCodes](https://youtu.be/5KEObONUkik?si=QYVU4lu8tpfmyTXV). This video really helped me to write a python Package and published it to the [PyPi](pypi.org)
+ 
+# Hi, I'm Jaideepsinh Dabhi (jD)! 👋
+
+
+## 🚀 About Me
+
+🚀 Data Scientist | Analytics Enthusiast | Python Aficionado 🐍 \
+I'm a Data Scientist working in a BioTech Industry.\
+I am based out of India 🇮🇳 \
+I love to code in python ,Bash and R \
+I have a strong base in statistics and Machine learning \
+I am passionate about networking and fostering meaningful connections within the tech community. Feel free to reach out if you'd like to discuss Data Science 👨🏻‍💻, Machine Learning 🦾, Chess ♞ or Pens 🖋️
+
+
+## 🔗 Links
+[![GitHub](https://img.shields.io/badge/my_portfolio-000?style=for-the-badge&logo=ko-fi&logoColor=white)](https://github.com/jaideepsinhdabhi)
+[![linkedin](https://img.shields.io/badge/linkedin-0A66C2?style=for-the-badge&logo=linkedin&logoColor=white)](https://www.linkedin.com/in/jaideepsinh-d-543476167/)
+
+
+
+## License
+
+This project is licensed under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0)

JustDataML-0.0.26.dist-info/RECORD

@@ -0,0 +1,19 @@
+JDML/JDML.py,sha256=W1bLCfqJjlv28jZw3DOauR7orB5K6S-324cllsXYmNo,6736
+JDML/__init__.py,sha256=JvBMwcE9Lye9-8HZI2rKCPjBdunrBedsMW4dpRfn-Tk,8
+JDML/source/Configuration.py,sha256=r3r8uQf9nxlbiz2Zs9FsMb9_tcg-0PKN6juZ2NQ_jto,2596
+JDML/source/Exception.py,sha256=gNGdFUci-iZSopoFWGxr0f-Fsrm-Oc4RdOHrSlbcbLM,636
+JDML/source/Logger.py,sha256=2G5XlkziDT2sKX96cL0wh7f4GLyAGr45Le--9ldKcLU,474
+JDML/source/Utils.py,sha256=a7kmaLjq5jX2SwXvdc_KHCVlK1pao9kIP5rtjwZysps,13717
+JDML/source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+JDML/source/Pipeline/Predict_Pipeline.py,sha256=NgQPPQh2U37tyb_9mHARtcDaBRJtIVkTnLPv10nqqZM,86942
+JDML/source/Pipeline/Train_Pipeline.py,sha256=Wa-l2Zo-DLvAJEF-hwbabKKT4SQKdEMqOzgoOXPNmx4,1935
+JDML/source/Pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+JDML/source/components/Data_Transformation.py,sha256=3eultgHPZ3ZSFIK5-kx0W6OcvhfznqHrITQnfisdtBA,6604
+JDML/source/components/Data_ingestion.py,sha256=awQofJ33JG4MrNRFRsvOaQrPa3XFr4TRlyMtjl7QgyI,1916
+JDML/source/components/Model_Trainer.py,sha256=cO-6mksI8IP_wiQb_9bF3djL7t2jJvhaQY-G1yT8Gw4,4028
+JDML/source/components/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+JustDataML-0.0.26.dist-info/METADATA,sha256=oEeAF-kq8CwOXaaCMvsfb3n--OQRXuZg_Jh0AyeDQOM,10934
+JustDataML-0.0.26.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
+JustDataML-0.0.26.dist-info/entry_points.txt,sha256=-kpNjSUFAaqE-eIhx3JpZUJZplbu05_gUejVCFkv2T0,42
+JustDataML-0.0.26.dist-info/top_level.txt,sha256=wpT5y6dLBGoQVit7ia4ZFyCIlUTDnH1A50Tx5k8r3x0,5
+JustDataML-0.0.26.dist-info/RECORD,,

JustDataML-0.0.26.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: bdist_wheel (0.41.2)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

JustDataML-0.0.26.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+JDML = JDML.JDML:MLtool

JustDataML-0.0.26.dist-info/top_level.txt

@@ -0,0 +1 @@
+JDML