Merge pull request #2 from Jaykold/client-side

Client side

.pre-commit-config.yaml

@@ -0,0 +1,17 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.2.0
+    hooks:
+    - id: trailing-whitespace
+    - id: end-of-file-fixer
+    - id: check-yaml
+    - id: check-added-large-files
+    - id: detect-private-key
+    - id: requirements-txt-fixer
+    - id: check-merge-conflict
+    - id: name-tests-test
+-   repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+    - id: isort
+      name: isort (python)

Makefile

@@ -1,10 +1,11 @@
+# For windows, use the following command to run the makefile
 PYTHON := python
 
 # Define the scripts
 DATA_TRAINING := src/components/model_trainer.py
 
 # Default target
-all: preprocess	
+all: preprocess
 
 # Target to run model training
 preprocess: ensure_artifacts_dir
@@ -24,35 +25,25 @@ clean:
 .PHONY: all preprocess clean ensure_artifacts_dir
 
 
+# # for linux, use the following command to run the makefile
+# PYTHON := python3
 
-# Makefile for ML Project
-
-# Variables
-TRAIN_DATA_PATH = artifacts/train_data.csv
-VALIDATE_DATA_PATH = artifacts/validate_data.csv
-TRAIN_SCRIPT = src/components/model_trainer.py
-DATA_INGEST_SCRIPT = src/components/data_ingestion.py
-DATA_PREPROCESS_SCRIPT = src/components/data_preprocessing.py
-
-# Targets
-
-.PHONY: all data_ingest preprocess train clean
-
-all: data_ingest preprocess train
+# Define the scripts
+# DATA_TRAINING := src/components/model_trainer.py
 
-data_ingest:
-	@echo "Running Data Ingestion..."
-	python $(DATA_INGEST_SCRIPT) --train_data $(TRAIN_DATA_PATH) --validate_data $(VALIDATE_DATA_PATH)
+# # Default target
+# all: preprocess
 
-preprocess: data_ingest
-	@echo "Running Data Preprocessing..."
-	python $(DATA_PREPROCESS_SCRIPT) --train_data $(TRAIN_DATA_PATH) --validate_data $(VALIDATE_DATA_PATH)
+# # Target to run model training
+# preprocess: ensure_artifacts_dir
+# 	$(PYTHON) $(DATA_TRAINING)
 
-train: preprocess
-	@echo "Running Model Training..."
-	python $(TRAIN_SCRIPT) --train_data $(TRAIN_DATA_PATH) --validate_data $(VALIDATE_DATA_PATH)
+# ensure_artifacts_dir:
+# 	mkdir -p artifacts
 
-clean:
-	@echo "Cleaning up..."
-	rm -rf artifacts/ logs/
+# # Clean target (optional)
+# clean:
+# 	rm -f *.pyc
+# 	rm -rf __pycache__
 
+# .PHONY: all preprocess clean ensure_artifacts_dir

README.md

@@ -61,32 +61,24 @@ To run this project, you need to install the following packages:
 
 ### Clone the repository
 
-```git clone https://github.com/Jaykold/dry-bean-predictor.git```
+```
+git clone https://github.com/Jaykold/dry-bean-predictor.git
+```
 
 ### Navigate to the project directory
 
-```cd dry-bean-predictor```
+```
+cd dry-bean-predictor
+```
 
 ### Create a virtual environment
-You can install the required packages using the provided`conda_dependencies.yml` file:
+You can install the required packages using the code provided below:
 
-```conda env create -f conda_dependencies.yml```
+```
+pip install -e .
+```
+Run this to install the required packages and project in editable mode.
 
-After creating your virtual environment, you can activate it using:
-
-<codespace/>```conda activate myenv // That's is the name specified in the .yml file```</codespace>
-
-Or using `requirements.txt`:
-
-```pip install -r requirements.txt```
-
-Run ```pip install -e .``` to install the project in editable mode.
-
-Run Jupyter Notebook
-
-```jupyter notebook```
-
-Open `dry_bean.ipynb` and execute the cells to preprocess the data and train the model
 
 ## Components
 
@@ -106,9 +98,47 @@ The `pipeline` directory contains script for model prediction.
 #### Model training
 To train the model, run the `model_trainer.py` script:
 
-```python src/components/model_trainer.py```
+```
+python src/components/model_trainer.py
+```
+
+Or use the Makefile by typing ```make``` in your terminal
 
 This will train the model and save the results to the `artifacts` directory.
 
+If you are using windows you can install ```make``` by running this code in your terminal
+
+```
+Set-ExecutionPolicy Bypass -Scope Process -Force; [System.Net.WebClient]::new().DownloadString('https://community.chocolatey.org/install.ps1') | Invoke-Expression
+```
+
+then install make using choco
+
+```
+choco install make
+```
+On linux check if ```make``` is installed
+
+```
+make --version
+```
+
+if not installed, run
+
+```
+sudo apt update
+sudo apt install make
+```
+.
+
+To run app.py to predict your bean, use this code command
+
+```
+# On windows
+waitress-serve --listen=0.0.0.0:9696 app:app
+# On Linux
+gunicorn --bind=0.0.0.0:9696 app:app
+```
+
 ## Contributing
 Contributions are welcome! Please open an issue or submit a pull request for any improvements or bug fixes.

notebook/dry_bean.ipynb

@@ -1,5 +1,46 @@
 {
  "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The raw dataset for this study was obtained from the UCI Machine Learning Repository via an API call using ```ucimlrepo``` (fetch_ucirepo). \n",
+    "\n",
+    "It included grains with 16 features in total, comprising 12 dimensions and 4 distinct shapes. The study employed three well-known \n",
+    "\n",
+    "classifiers: Logistic Regression (LR), Random Forest (RF), and \n",
+    "\n",
+    "Extreme Gradient Boosting (XGB), all with balanced classes.\n",
+    "\n",
+    "This dataset has a shape of 13,611 data entries and 17 columns\n",
+    "\n",
+    "1. **Area (A)**: The area of a bean zone and the number of pixels within its boundaries.\n",
+    "\n",
+    "2. **Perimeter (P)**: Bean circumference is defined as the length of its border.\n",
+    "3. **Major axis length (L)**: The distance between the ends of the longest line that can be drawn from a bean.\n",
+    "4. **Minor axis length (l)**: The longest line that can be drawn from the bean while standing perpendicular to the main axis.\n",
+    "5. **Aspect ratio (K)**: Defines the relationship between L and l.\n",
+    "6. **Eccentricity (Ec)**: Eccentricity of the ellipse having the same moments as the region.\n",
+    "7. **Convex area (C)**: Number of pixels in the smallest convex polygon that can contain the area of a bean seed.\n",
+    "8. **Equivalent diameter (Ed)**: The diameter of a circle having the same area as a bean seed area.\n",
+    "9. **Extent (Ex)**: The ratio of the pixels in the bounding box to the bean area.\n",
+    "10. **Solidity (S)**: Also known as convexity. The ratio of the pixels in the convex shell to those found in beans.\n",
+    "11. **Roundness (R)**: Calculated with the following formula: \\( \\frac{4\\pi A}{P^2} \\)\n",
+    "12. **Compactness (CO)**: Measures the roundness of an object: \\( \\frac{Ed}{L} \\)\n",
+    "13. **ShapeFactor1 (SF1)**\n",
+    "14. **ShapeFactor2 (SF2)**\n",
+    "15. **ShapeFactor3 (SF3)**\n",
+    "16. **ShapeFactor4 (SF4)**\n",
+    "17. **Class**: Seker, Barbunya, Bombay, Cali, Dermosan, Horoz, and Sira"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "code",
    "execution_count": 1,
@@ -97,7 +138,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df = pd.read_csv('data/dry_bean.csv')"
+    "# df = pd.read_csv('data/dry_bean.csv')"
    ]
   },
   {

requirements.txt

@@ -1,17 +1,18 @@
-mlflow
+evidently
+Flask
+gunicorn
+imbalanced-learn
 jupyter
-scikit-learn
+mlflow
 pandas
-seaborn
-ucimlrepo
-xgboost
-imbalanced-learn
-Flask
-tdqm
+pre-commit
+psycopg
 pydantic
 pylint
-evidently
-psycopg
 pytest
 pytest-flask
-gunicorn
+scikit-learn
+seaborn
+tdqm
+ucimlrepo
+xgboost

src/pipeline/predict.py

@@ -1,10 +1,13 @@
 import sys
 from typing import Union
+
 import pandas as pd
 from pydantic import BaseModel
+
 from src.exception import CustomException
 from src.utils import load_object
 
+
 class PredictPipeline:
     def __init__(self):
         pass
@@ -15,7 +18,7 @@ def predict(self, features:pd.DataFrame):
             model_path = 'artifacts/model.pkl'
             scaler_path = 'artifacts/scaler.pkl'
             labelencoder_path = 'artifacts/labelencoder.pkl'
-            
+
             # Load the model, SMOTE, and scaler objects
             model = load_object(file_path=model_path)
             scaler = load_object(file_path=scaler_path)
@@ -24,10 +27,10 @@ def predict(self, features:pd.DataFrame):
             # Transform the features using scaler
             data_scaled = scaler.transform(features)
             # Make predictions using the model
-            pred = model.predict(data_scaled)#.astype(int)
+            pred = model.predict(data_scaled).astype(int)
             result = labelencoder.inverse_transform(pred)
             return result[0].capitalize()
-        
+
         except Exception as e:
             # Raise a custom exception if an error occurs
             raise CustomException(e, sys) from e
@@ -71,6 +74,6 @@ def to_dataframe(self):
                         'ShapeFactor4': [self.ShapeFactor4]
                     }
                     return pd.DataFrame(data)
-                
+
                 except Exception as e:
-                    raise CustomException(e, sys) from e
+                    raise CustomException(e, sys) from e

static/css/home.css

@@ -14,11 +14,12 @@ body {
 }
 
 .login {
-    width: 400px;
+    width: 100%;
     padding: 20px;
     border: 1px solid #ccc;
     border-radius: 10px;
     box-shadow: 0 0 10px rgba(0, 0, 0, 0.1);
+    max-width: 700px;
 }
 
 .heading {
@@ -88,3 +89,16 @@ body {
 .dropdown-item:hover {
     background-color: #f0f0f0;
 }
+
+.two-grid{
+    display: flex;
+    flex-direction: row;
+    justify-content: space-between;
+    gap: 10px;
+}
+.two-grid-child{
+    width: 48%;
+    display: flex;
+    flex-direction: column;
+    gap: 20px;
+}

static/js/index.js

@@ -31,25 +31,44 @@ const dropDownChild = document.createElement('div');
         console.log("input value",input.value)
         areaDropDown.style.display = 'none'; // Hide dropdown after selection
     });
-    
+
     dropDown.appendChild(dropDownChild);
 });}
 
-const areaValues = [1, 2, 3, 4, 5, 6];
+const areaValues = [71236, 39318, 34045];
 
 const areaInput = document.getElementById("area-input");
 const areaDropDown = document.getElementById("area-dropdown");
 
 populateDropdown(areaInput, areaDropDown, areaValues)
 
 
-const perimeterValues = [1, 2, 3, 4, 5, 6, 7];
+const perimeterValues = [1055.392, 746.921, 681.927];
 const perimeterInput = document.getElementById("perimeter-input");
 const perimeterDropDown = document.getElementById("perimeter-dropdown");
 
 populateDropdown(perimeterInput, perimeterDropDown, perimeterValues)
 
+const majoraxislengthValues = [345.968599, 279.815434, 252.167650];
+const majoraxislengthInput = document.getElementById("majoraxislength-input");
+const majoraxislengthDropDown = document.getElementById("majoraxislength-dropdown");
+
+populateDropdown(majoraxislengthInput, majoraxislengthDropDown, majoraxislengthValues)
+
+const minoraxislengthValues = [264.740746, 179.451019, 172.362100];
+const minoraxislengthInput = document.getElementById("minoraxislength-input");
+const minoraxislengthDropDown = document.getElementById("minoraxislength-dropdown");
+
+populateDropdown(minoraxislengthInput, minoraxislengthDropDown, minoraxislengthValues)
 
+const aspectratioValues = [1.487857, 2.092897, 1.606084];
+const aspectratioInput = document.getElementById("aspectratio-input");
+const aspectratioDropDown = document.getElementById("aspectratio-dropdown");
 
+populateDropdown(aspectratioInput, aspectratioDropDown, aspectratioValues)
 
+const eccentricityValues = [0.740453, 0.878465, 0.782514];
+const eccentricityInput = document.getElementById("eccentricity-input");
+const eccentricityDropDown = document.getElementById("eccentricity-dropdown");
 
+populateDropdown(eccentricityInput, eccentricityDropDown, eccentricityValues)