Upload 13 files

Monitor_reports/regression_performance_at_training.json

@@ -0,0 +1 @@
+{"version": "0.6.5", "metrics": [{"metric": "RegressionQualityMetric", "result": {"columns": {"utility_columns": {"date": null, "id": null, "target": "GrdAmt", "prediction": "adjusted_pred"}, "num_feature_names": ["EngAmt", "EngCts"], "cat_feature_names": ["Tag", "EngShp", "EngQua", "EngCol", "EngCut", "EngPol", "EngSym", "EngFlo", "EngNts", "EngMikly", "EngLab"], "text_feature_names": [], "datetime_feature_names": [], "target_names": null}, "current": {"r2_score": 0.9999923028920211, "rmse": 1.7576599997312332, "mean_error": 0.12982898322209938, "mean_abs_error": 1.4146422000467425, "mean_abs_perc_error": 0.36231777831306916, "abs_error_max": 3.0279654590704013, "underperformance": {"majority": {"mean_error": 0.12798954903896345, "std_error": 1.0911472758726741}, "underestimation": {"mean_error": -2.759110321710523, "std_error": NaN}, "overestimation": {"mean_error": 3.0279654590704013, "std_error": NaN}}, "error_std": 1.8933036280707416, "abs_error_std": 1.1267277727646234, "abs_perc_error_std": 0.003736499656151631}, "reference": null, "rmse_default": 633.5356812819848, "me_default_sigma": 1.8933036280707416, "mean_abs_error_default": 363.31442857142855, "mean_abs_perc_error_default": 47.842013429798385, "abs_error_max_default": 1763.2030000000002, "error_normality": {"order_statistic_medians_x": [-1.314872752547375, -0.7439764884519314, -0.3471943041728483, 0.0, 0.3471943041728483, 0.7439764884519314, 1.314872752547375], "order_statistic_medians_y": [-2.759110321710523, -1.347814805996677, -0.3899211311790509, 0.0004486202879263601, 1.0304255232912851, 1.3468095387913337, 3.0279654590704013], "slope": 2.103082399659136, "intercept": 0.12982898322209938, "r": 0.9941374379341389}, "error_bias": {"EngAmt": {"feature_type": "num", "current_majority": 601.6108571428571, "current_under": 1818.545, "current_over": 821.99, "current_range": 63.14647907315083}, "EngCts": {"feature_type": "num", "current_majority": 0.6328571428571428, "current_under": 1.01, "current_over": 0.96, "current_range": 7.042253521126767}, "Tag": {"feature_type": "cat", "current_majority": 0, "current_under": 0, "current_over": 0, "current_range": 0.0}, "EngShp": {"feature_type": "cat", "current_majority": 0, "current_under": 6, "current_over": 6, "current_range": 1.0}, "EngQua": {"feature_type": "cat", "current_majority": 7, "current_under": 7, "current_over": 2, "current_range": 1.0}, "EngCol": {"feature_type": "cat", "current_majority": 2, "current_under": 5, "current_over": 3, "current_range": 1.0}, "EngCut": {"feature_type": "cat", "current_majority": 5, "current_under": 2, "current_over": 5, "current_range": 1.0}, "EngPol": {"feature_type": "cat", "current_majority": 0, "current_under": 0, "current_over": 1, "current_range": 1.0}, "EngSym": {"feature_type": "cat", "current_majority": 1, "current_under": 0, "current_over": 1, "current_range": 1.0}, "EngFlo": {"feature_type": "cat", "current_majority": 2, "current_under": 2, "current_over": 2, "current_range": 0.0}, "EngNts": {"feature_type": "cat", "current_majority": 0, "current_under": 0, "current_over": 0, "current_range": 0.0}, "EngMikly": {"feature_type": "cat", "current_majority": 1, "current_under": 1, "current_over": 1, "current_range": 0.0}, "EngLab": {"feature_type": "cat", "current_majority": 1, "current_under": 1, "current_over": 1, "current_range": 0.0}}}}, {"metric": "RegressionPredictedVsActualScatter", "result": {}}, {"metric": "RegressionPredictedVsActualPlot", "result": {}}, {"metric": "RegressionErrorPlot", "result": {}}, {"metric": "RegressionAbsPercentageErrorPlot", "result": {}}, {"metric": "RegressionErrorDistribution", "result": {}}, {"metric": "RegressionErrorNormality", "result": {}}, {"metric": "RegressionTopErrorMetric", "result": {}}, {"metric": "RegressionErrorBiasTable", "result": {"top_error": -1.0, "target_name": "", "prediction_name": "", "num_feature_names": [], "cat_feature_names": [], "error_bias": null, "columns": null}}], "timestamp": "2025-03-07 15:33:42.729397"}

app2.py

@@ -0,0 +1,283 @@
+from flask import Flask, render_template, request, redirect, url_for, flash, send_file
+import os
+import pandas as pd
+from werkzeug.utils import secure_filename
+from joblib import load
+import numpy as np
+from sklearn.preprocessing import OneHotEncoder, LabelEncoder
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from sklearn.decomposition import PCA
+from sklearn.pipeline import Pipeline
+from sklearn.tree import DecisionTreeRegressor
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.linear_model import LinearRegression
+from xgboost import XGBRegressor
+from sklearn.neighbors import KNeighborsRegressor
+from sklearn.model_selection import cross_val_score
+from sklearn.metrics import mean_squared_error
+from sklearn import metrics
+from sklearn.metrics.pairwise import cosine_similarity
+from time import time
+
+app = Flask(__name__)
+
+# Set the secret key for session management
+app.secret_key = os.urandom(24)
+
+# Configurations
+UPLOAD_FOLDER = "uploads/"
+DATA_FOLDER = "data/"
+
+# Define the model directory (ensuring correct path formatting)
+MODEL_DIR = r'.\Model'
+LABEL_ENOCDER_DIR = r'.\Label_encoders'
+
+# Define the output file path
+PRED_OUTPUT_FILE = "data/pred_output.csv"
+CLASS_OUTPUT_FILE = "data/class_output.csv"
+
+ALLOWED_EXTENSIONS = {'csv', 'xlsx'}
+
+app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
+
+# Ensure the upload folder exists
+os.makedirs(app.config['UPLOAD_FOLDER'], exist_ok=True)
+
+# Load models using os.path.join for better cross-platform compatibility
+
+# linear_regression_model
+gia_model = load(os.path.join(MODEL_DIR, 'linear_regression_model_gia_price.joblib'))
+grade_model = load(os.path.join(MODEL_DIR, 'linear_regression_model_grade_price.joblib'))
+bygrade_model = load(os.path.join(MODEL_DIR, 'linear_regression_model_bygrade_price.joblib'))
+makable_model = load(os.path.join(MODEL_DIR, 'linear_regression_model_makable_price.joblib'))
+
+# classifier_model
+col_model = load(os.path.join(MODEL_DIR, 'classification_LogisticRegression_col.joblib'))
+cts_model = load(os.path.join(MODEL_DIR, 'classification_LogisticRegression_cts.joblib'))
+cut_model = load(os.path.join(MODEL_DIR, 'classification_LogisticRegression_cut.joblib'))
+qua_model = load(os.path.join(MODEL_DIR, 'classification_LogisticRegression_qua.joblib'))
+shp_model = load(os.path.join(MODEL_DIR, 'classification_LogisticRegression_shp.joblib'))
+
+# print("===================================models==================================")
+# print(gia_model)
+# print(grade_model)  
+# print(bygrade_model)
+# print(makable_model)
+
+# Load label encoders
+encoder_list = ['Tag', 'EngShp', 'EngQua', 'EngCol', 'EngCut', 'EngPol', 'EngSym', 'EngFlo', 'EngNts', 'EngMikly', 'EngLab',
+                'Change_cts_value', 'Change_shape_value', 'Change_quality_value', 'Change_color_value', 'Change_cut_value']
+#loaded_label_encoder = {val: load(f"./Label_encoders/label_encoder_{val}.joblib") for val in encoder_list}
+loaded_label_encoder = {}
+for val in encoder_list:
+    #encoder_path = f"H:/DEV PATEL/2025/AI_In_Diamond_Industry/Label_encoders/label_encoder_{val}.joblib"
+    encoder_path = os.path.join(LABEL_ENOCDER_DIR, f"label_encoder_{val}.joblib")
+    loaded_label_encoder[val] = load(encoder_path)
+    
+# print(loaded_label_encoder)
+
+# Ensure upload folder exists
+os.makedirs(UPLOAD_FOLDER, exist_ok=True)
+
+def allowed_file(filename):
+    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    if 'file' not in request.files:
+        flash('No file part', 'error')
+        return redirect(request.url)
+    
+    file = request.files['file']
+    if file.filename == '':
+        flash('No selected file', 'error')
+        return redirect(request.url)
+    
+    if file and allowed_file(file.filename):
+        filename = secure_filename(file.filename)
+        filepath = os.path.join(app.config['UPLOAD_FOLDER'], filename)
+        file.save(filepath)
+        
+        # Convert to DataFrame
+        if filename.endswith('.csv'):
+            df = pd.read_csv(filepath)
+        else:
+            df = pd.read_excel(filepath)
+        
+        # Preprocess DataFrame
+        print("===================================process_dataframe=0==================================")
+        df,dx = process_dataframe(df)
+        print("===================================process_dataframe=5==================================")
+        return render_template('output.html', df=df.to_html(), dx=dx.to_html())
+    else:
+        flash('Invalid file type. Only CSV and Excel files are allowed.', 'error')
+        print('Invalid file type. Only CSV and Excel files are allowed.')
+        return redirect(request.url)
+
+def process_dataframe(df):
+    try:
+        print("===================================process_dataframe=1==================================")
+        # 'EngLab' is not in the required columns
+        required_columns = ['Tag', 'EngCts', 'EngShp', 'EngQua', 'EngCol', 'EngCut', 'EngPol',
+                            'EngSym', 'EngFlo', 'EngNts', 'EngMikly', 'EngAmt']
+        
+        # for prediction
+        df = df[required_columns]
+        df = df.copy()
+        # for classification
+        
+        
+        # df[col] = df[col].map(lambda x: loaded_label_encoder[col].transform([x])[0] if x in loaded_label_encoder[col].classes_ else np.nan)
+
+        # Transform categorical features using loaded label encoders
+        df["Tag"] = loaded_label_encoder['Tag'].transform(df["Tag"])
+        df["EngShp"] = loaded_label_encoder['EngShp'].transform(df["EngShp"]) 
+        df["EngQua"] = loaded_label_encoder['EngQua'].transform(df["EngQua"])
+        df["EngCol"] = loaded_label_encoder['EngCol'].transform(df["EngCol"])
+        df["EngCut"] = loaded_label_encoder['EngCut'].transform(df["EngCut"])
+        df["EngPol"] = loaded_label_encoder['EngPol'].transform(df["EngPol"])
+        df["EngSym"] = loaded_label_encoder['EngSym'].transform(df["EngSym"])
+        df["EngFlo"] = loaded_label_encoder['EngFlo'].transform(df["EngFlo"])
+        df["EngNts"] = loaded_label_encoder['EngNts'].transform(df["EngNts"])
+        df["EngMikly"] = loaded_label_encoder['EngMikly'].transform(df["EngMikly"])
+        #EngLab = loaded_label_encoder['EngLab'].transform(df[EngLab])
+        
+        df=df.astype(float)
+        print(df.head())  
+          
+        dx = df.copy()
+        
+        print(df.columns)
+        x= df.copy()
+        
+        # print("Model expects", gia_model.n_features_in_, "features.")
+        # print("X_features shape:", x.shape)
+        
+        print("===================================process_dataframe=2==================================")
+        
+        # ================================================================================================
+        # Prediction report
+        # ================================================================================================
+        
+        # Predict prices
+        df['GIA_Predicted'] = gia_model.predict(x)
+        df['Grade_Predicted'] = grade_model.predict(x)
+        df['ByGrade_Predicted'] = bygrade_model.predict(x)
+        df['Makable_Predicted'] = makable_model.predict(x)
+                            
+        
+        # Compute differences
+        df['GIA_Diff'] = df['EngAmt'] - df['GIA_Predicted']
+        df['Grade_Diff'] = df['EngAmt'] - df['Grade_Predicted']
+        df['ByGrade_Diff'] = df['EngAmt'] - df['ByGrade_Predicted']
+        df['Makable_Diff'] = df['EngAmt'] - df['Makable_Predicted']
+        
+        print(df.head())
+        
+        predictions = df.to_dict(orient='records')
+        analysis = df.describe().to_html()
+        #print(analysis)
+        #print(predictions)
+        print("===================================process_dataframe=3==================================")
+        
+        # ================================================================================================
+        # Classification report
+        # ================================================================================================      
+                      
+        dx['col_change'] = col_model.predict(x)
+        dx['cts_change'] = cts_model.predict(x)
+        dx['cut_change'] = cut_model.predict(x)
+        dx['qua_change'] = qua_model.predict(x)
+        dx['shp_change'] = shp_model.predict(x)
+        
+        # Inverse transform the predictions
+        dx['col_change'] = loaded_label_encoder['Change_color_value'].inverse_transform(dx['col_change'])
+        dx['cts_change'] = loaded_label_encoder['Change_cts_value'].inverse_transform(dx['cts_change'])
+        dx['cut_change'] = loaded_label_encoder['Change_cut_value'].inverse_transform(dx['cut_change'])
+        dx['qua_change'] = loaded_label_encoder['Change_quality_value'].inverse_transform(dx['qua_change'])
+        dx['shp_change'] = loaded_label_encoder['Change_shape_value'].inverse_transform(dx['shp_change'])   
+        
+        print(dx.head())     
+        
+        print("===================================process_dataframe=4==================================")
+        
+        # Save output file with date and time
+        time = str(pd.Timestamp.now().strftime("%Y-%m-%d"))
+        
+        #saving the output file
+        global PRED_OUTPUT_FILE
+        PRED_OUTPUT_FILE = f'data/prediction_output_{time}.csv'
+        df.to_csv(PRED_OUTPUT_FILE, index=False)
+        
+        #saving the output file
+        global CLASS_OUTPUT_FILE
+        CLASS_OUTPUT_FILE = f'data/classification_output_{time}.csv'
+        dx.to_csv(CLASS_OUTPUT_FILE, index=False)
+        
+        print("===================================Output file saved as output.csv===================================")
+        
+        return df.head(), dx.head()
+    except Exception as e:
+        print(f'Error processing file: {e}')
+        flash(f'Error processing file: {e}', 'error')
+        return pd.DataFrame(), pd.DataFrame()
+    
+def classification_report(df):
+    try:
+        classifcation_data = df[["EngGraphCts","EngCts","EngShp","EngQua","EngCol","EngCut","EngPol","EngSym","EngFlo","EngNts","EngMikly","EngLab","EngAmt",
+                                 "MkblCts","MkblShp","MkblQua","MkblCol","MkblCut","MkblPol","MkblSym","MkblFlo","MkblNts","MkblMikly","MkblLab","MkblAmt"]] 
+        
+        # Make predictions
+        classifcation_data["Cts_diff_eng_mkbl"] = round(classifcation_data["EngCts"] - classifcation_data["MkblCts"],2)
+
+        # Create a new column 'Change_Label' based on the values in 'Cts_diff_eng_mkbl'
+        classifcation_data['Change_cts_value'] = classifcation_data['Cts_diff_eng_mkbl'].apply(
+            lambda x: str(x)+' negative change' if x < 0 else (str(x)+' positive change' if x > 0 else 'no change')
+        )
+        
+        # Create a new column 'Shape_Change' based on the values in 'EngShp' and 'MkblShp'
+        classifcation_data['Change_shape_value'] = classifcation_data.apply(
+            lambda row: str(row['EngShp'])+' to '+str(row['MkblShp'])+' shape change' if row['EngShp'] != row['MkblShp'] else 'shape not change', axis=1
+        )
+        
+        # Create a new column 'quality_Change' based on the values in 'EngQua' and 'MkblQua'
+        classifcation_data['Change_quality_value'] = classifcation_data.apply(
+            lambda row: str(row['EngQua'])+' to '+str(row['MkblQua'])+' quality change' if row['EngQua'] != row['MkblQua'] else 'quality not change', axis=1
+        )
+        
+        # Create a new column 'color_Change' based on the values in 'EngCol' and 'MkblCol'
+        classifcation_data['Change_color_value'] = classifcation_data.apply(
+            lambda row: str(row['EngCol'])+' to '+str(row['MkblCol'])+' color change' if row['EngCol'] != row['MkblCol'] else 'color not change', axis=1
+        )
+        
+        # Create a new column 'cut_Change' based on the values in 'EngCut' and 'MkblCut'
+        classifcation_data['Change_cut_value'] = classifcation_data.apply(
+            lambda row: str(row['EngCut'])+' to '+str(row['MkblCut'])+' cut change' if row['EngCut'] != row['MkblCut'] else 'cut not change', axis=1
+        )
+        
+        # Generate classification report
+        
+        
+        return classifcation_data
+    except Exception as e:
+        flash(f'Error generating classification report: {e}', 'error')
+        print(f'Error generating classification report: {e}')
+        return None
+    
+@app.route('/download_pred', methods=['GET'])
+def download_pred():
+    """Serve the output.csv file for download."""
+    return send_file(PRED_OUTPUT_FILE, as_attachment=True)  
+
+@app.route('/download_class', methods=['GET'])
+def download_class():
+    """Serve the output.csv file for download."""
+    return send_file(CLASS_OUTPUT_FILE, as_attachment=True)   
+
+if __name__ == "__main__":
+    app.run(debug=True)

requirement.txt

@@ -0,0 +1,97 @@
+absl-py
+asttokens
+astunparse
+blinker
+certifi
+charset-normalizer
+click
+colorama
+comm
+contourpy
+cycler
+debugpy
+decorator
+et_xmlfile
+executing
+filelock
+Flask
+flatbuffers
+fonttools
+fsspec
+gast
+google-pasta
+grpcio
+h5py
+idna
+ipykernel
+ipython
+itsdangerous
+jedi
+Jinja2
+joblib
+jupyter_client
+jupyter_core
+keras
+kiwisolver
+libclang
+Markdown
+markdown-it-py
+MarkupSafe
+matplotlib
+matplotlib-inline
+mdurl
+ml-dtypes
+mpmath
+namex
+nest-asyncio
+networkx
+numpy
+openpyxl
+opt_einsum
+optree
+packaging
+pandas
+parso
+patsy
+pillow
+platformdirs
+prompt_toolkit
+protobuf
+psutil
+pure_eval
+Pygments
+pyparsing
+python-dateutil
+python-dotenv
+pytz
+pywin32
+pyzmq
+requests
+rich
+scikit-learn
+scipy
+seaborn
+setuptools
+six
+stack-data
+statsmodels
+sympy
+tensorboard
+tensorboard-data-server
+tensorflow
+tensorflow_intel
+termcolor
+threadpoolctl
+torch
+torchaudio
+torchvision
+tornado
+traitlets
+typing_extensions
+tzdata
+urllib3
+wcwidth
+Werkzeug
+wheel
+wrapt
+xgboost

templates/home.html

@@ -0,0 +1,219 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <title>Diamond Price Prediction</title>
+  <style>
+    body {
+      background-color: #041C32;
+      color: #ECB365;
+      font-family: Arial, sans-serif;
+      margin: 0;
+      padding: 20px;
+    }
+    .container {
+      max-width: 800px;
+      margin: auto;
+      background-color: #04293A;
+      padding: 20px;
+      border-radius: 8px;
+    }
+    h1 {
+      color: #ECB365;
+    }
+    label {
+      display: block;
+      margin-top: 10px;
+      color: #ECB365;
+    }
+    input[type="text"],
+    input[type="number"],
+    select {
+      width: 100%;
+      padding: 8px;
+      margin-top: 5px;
+      border: 1px solid #064663;
+      border-radius: 4px;
+      background-color: #064663;
+      color: #ECB365;
+      box-sizing: border-box;
+    }
+    .btn {
+      margin-top: 20px;
+      padding: 10px 15px;
+      background-color: #ECB365;
+      color: #041C32;
+      border: none;
+      border-radius: 4px;
+      cursor: pointer;
+      font-weight: bold;
+    }
+    .flash {
+      padding: 10px;
+      margin-bottom: 15px;
+      border: 1px solid #ECB365;
+      background-color: #064663;
+    }
+  </style>
+</head>
+<body>
+  <div class="container">
+    <h1>Diamond Price Prediction</h1>
+    <p><strong>Note:</strong>there may be values missing in option due to less data.</p>
+    {% with messages = get_flashed_messages(with_categories=true) %}
+      {% if messages %}
+        {% for category, message in messages %}
+          <div class="flash">{{ message }}</div>
+        {% endfor %}
+      {% endif %}
+    {% endwith %}
+    <form action="{{ url_for('predict') }}" method="post">
+
+      <!-- Fixed dropdown fields -->
+      <label for="Tag">Tag (Category)</label>
+      <select id="Tag" name="Tag">
+        <option value="">Select Tag</option>
+        <option value="A">A</option>
+        <option value="B">B</option>
+        <option value="C">C</option>
+        <option value="D">D</option>
+        <option value="E">E</option>
+        <option value="F">F</option>
+        <option value="G">G</option>
+        <option value="H">H</option>
+        <option value="I">I</option>
+      </select>
+
+      <label for="EngShp">EngShp</label>
+      <select id="EngShp" name="EngShp">
+        <option value="">Select EngShp</option>
+        <option value="OV">OV</option>
+        <option value="MQ">MQ</option>
+        <option value="PE">PE</option>
+        <option value="R">R</option>
+        <option value="EM">EM</option>
+        <option value="HR">HR</option>
+        <option value="RD">RD</option>
+        <option value="PR">PR</option>
+      </select>
+
+      <label for="EngQua">EngQua</label>
+      <select id="EngQua" name="EngQua">
+        <option value="">Select EngQua</option>
+        <option value="SI2">SI2</option>
+        <option value="SI1">SI1</option>
+        <option value="VS2">VS2</option>
+        <option value="VVS2">VVS2</option>
+        <option value="VS1">VS1</option>
+        <option value="I2">I2</option>
+        <option value="I1">I1</option>
+        <option value="I2-">I2-</option>
+        <option value="I3">I3</option>
+        <option value="SI3">SI3</option>
+        <option value="I1-">I1-</option>
+        <option value="I4">I4</option>
+        <option value="I5">I5</option>
+        <option value="VVS1">VVS1</option>
+      </select>
+
+      <label for="EngCol">EngCol</label>
+      <select id="EngCol" name="EngCol">
+        <option value="">Select EngCol</option>
+        <option value="G">G</option>
+        <option value="F">F</option>
+        <option value="H">H</option>
+        <option value="E">E</option>
+        <option value="I">I</option>
+        <option value="J">J</option>
+        <option value="D">D</option>
+        <option value="L">L</option>
+        <option value="K">K</option>
+        <option value="M">M</option>
+      </select>
+
+      <label for="EngCut">EngCut</label>
+      <select id="EngCut" name="EngCut">
+        <option value="">Select EngCut</option>
+        <option value="EX3">EX3</option>
+        <option value="VG1">VG1</option>
+        <option value="EX1">EX1</option>
+        <option value="EX4">EX4</option>
+        <option value="EX2">EX2</option>
+        <option value="GD1">GD1</option>
+      </select>
+
+      <label for="EngPol">EngPol</label>
+      <select id="EngPol" name="EngPol">
+        <option value="">Select EngPol</option>
+        <option value="EX">EX</option>
+        <option value="VG">VG</option>
+      </select>
+
+      <label for="EngSym">EngSym</label>
+      <select id="EngSym" name="EngSym">
+        <option value="">Select EngSym</option>
+        <option value="EX">EX</option>
+        <option value="VG">VG</option>
+      </select>
+
+      <label for="EngFlo">EngFlo</label>
+      <select id="EngFlo" name="EngFlo">
+        <option value="">Select EngFlo</option>
+        <option value="Non">Non</option>
+        <option value="Fnt">Fnt</option>
+        <option value="Med">Med</option>
+        <option value="Str">Str</option>
+        <option value="VStr">VStr</option>
+      </select>
+
+      <label for="EngNts">EngNts</label>
+      <select id="EngNts" name="EngNts">
+        <option value="">Select EngNts</option>
+        <option value="N">N</option>
+        <option value="NTS2">NTS2</option>
+        <option value="NTS1">NTS1</option>
+        <option value="RSP-1">RSP-1</option>
+      </select>
+
+      <label for="EngMikly">EngMikly</label>
+      <select id="EngMikly" name="EngMikly">
+        <option value="">Select EngMikly</option>
+        <option value="N">N</option>
+        <option value="ML1">ML1</option>
+        <option value="Nv">Nv</option>
+      </select>
+
+      <label for="EngLab">EngLab</label>
+      <select id="EngLab" name="EngLab">
+        <option value="">Select EngLab</option>
+        <option value="nan">None</option>
+        <option value="IGI">IGI</option>
+      </select>
+
+      <!-- Other input fields remain for user to fill manually -->
+      <!-- <label for="ICarat">ICarat</label>
+      <input type="number" step="any" id="ICarat" name="ICarat" placeholder="Enter ICarat">
+
+      <label for="MkblCarat">MkblCarat</label>
+      <input type="number" step="any" id="MkblCarat" name="MkblCarat" placeholder="Enter MkblCarat">
+
+      <label for="SawLossCarat">SawLossCarat</label>
+      <input type="number" step="any" id="SawLossCarat" name="SawLossCarat" placeholder="Enter SawLossCarat">
+
+      <label for="CrapsCarat">CrapsCarat</label>
+      <input type="number" step="any" id="CrapsCarat" name="CrapsCarat" placeholder="Enter CrapsCarat">
+
+      <label for="EngGraphCts">EngGraphCts</label>
+      <input type="number" step="any" id="EngGraphCts" name="EngGraphCts" placeholder="Enter EngGraphCts"> -->
+
+      <label for="EngCts">EngCts</label>
+      <input type="number" step="any" id="EngCts" name="EngCts" placeholder="Enter EngCts">
+
+      <label for="EngAmt">EngAmt</label>
+      <input type="number" step="any" id="EngAmt" name="EngAmt" placeholder="Enter EngAmt">
+
+      <button type="submit" class="btn">Predict Price</button>
+    </form>
+  </div>
+</body>
+</html>

templates/index.html

@@ -0,0 +1,70 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <title>Diamond Price Prediction</title>
+  <style>
+    body {
+      background-color: #041C32;
+      color: #ECB365;
+      font-family: Arial, sans-serif;
+      margin: 0;
+      padding: 20px;
+    }
+    .container {
+      max-width: 800px;
+      margin: auto;
+      background-color: #04293A;
+      padding: 20px;
+      border-radius: 8px;
+    }
+    h1 {
+      color: #ECB365;
+      text-align: center;
+    }
+    label {
+      display: block;
+      margin-top: 10px;
+      color: #ECB365;
+    }
+    input, select {
+      width: 100%;
+      padding: 8px;
+      margin-top: 5px;
+      border: 1px solid #064663;
+      border-radius: 4px;
+      background-color: #064663;
+      color: #ECB365;
+      box-sizing: border-box;
+    }
+    .btn {
+      margin-top: 20px;
+      padding: 10px 15px;
+      background-color: #ECB365;
+      color: #041C32;
+      border: none;
+      border-radius: 4px;
+      cursor: pointer;
+      font-weight: bold;
+    }
+    .upload-section {
+      margin-top: 20px;
+      padding: 15px;
+      border: 2px dashed #ECB365;
+      text-align: center;
+    }
+  </style>
+</head>
+<body>
+  <div class="container">
+    <h1>Diamond Price Prediction</h1>
+    <div class="upload-section">
+      <h3>Upload CSV or Excel for Bulk Prediction</h3>
+      <form action="{{ url_for('predict') }}" method="post" enctype="multipart/form-data">
+        <input type="file" name="file" accept=".csv, .xlsx" required>
+        <button type="submit" class="btn">Upload & Predict</button>
+      </form>
+    </div>
+  </div>
+</body>
+</html>

templates/output.html

@@ -0,0 +1,97 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <title>Prediction Result</title>
+  <style>
+    body {
+      background-color: #041C32;
+      color: #ECB365;
+      font-family: Arial, sans-serif;
+      margin: 0;
+      padding: 20px;
+    }
+    .container {
+      max-width: 900px;
+      margin: auto;
+      background-color: #04293A;
+      padding: 20px;
+      border-radius: 8px;
+      text-align: center;
+    }
+    h1 {
+      color: #ECB365;
+    }
+    .result-box {
+      padding: 20px;
+      margin-top: 15px;
+      border: 2px solid #ECB365;
+      background-color: #064663;
+      font-size: 1em;
+      font-weight: normal;
+      border-radius: 5px;
+    }
+    .btn {
+      margin-top: 20px;
+      padding: 10px 15px;
+      background-color: #ECB365;
+      color: #041C32;
+      border: none;
+      border-radius: 4px;
+      cursor: pointer;
+      font-weight: bold;
+      display: inline-block;
+      text-decoration: none;
+    }
+    /* Styles for the table container */
+    .table-wrapper {
+      overflow-x: auto;
+      margin: auto;
+      max-width: 100%;
+      padding: 10px;
+      background-color: #04293A;
+      border-radius: 4px;
+    }
+    table {
+      width: 100%;
+      border-collapse: collapse;
+      color: #ECB365;
+    }
+    th, td {
+      border: 1px solid #ECB365;
+      padding: 8px;
+      text-align: center;
+    }
+    th {
+      background-color: #064663;
+      font-weight: bold;
+    }
+  </style>
+</head>
+<body>
+  <!--Prediction Report-->
+  <div class="container">
+    <h1>Predicted Diamond Price</h1>
+    <div class="result-box">
+      <p>The Prediction on diamond:</p>
+      <div class="table-wrapper">
+        {{ df|safe }}
+      </div>
+    </div>
+    <a href="{{ url_for('download_pred') }}" class="btn">Download CSV</a>
+    <a href="/" class="btn">Go Back</a>
+  </div>
+  <!--Analysis Report-->
+  <div class="container">
+    <h1>Analysis Diamond Parameter changes</h1>
+    <div class="result-box">
+      <p>The analysis on diamond:</p>
+      <div class="table-wrapper">
+        {{ dx|safe }}
+      </div>
+    </div>
+    <a href="{{ url_for('download_class') }}" class="btn">Download CSV</a>
+    <a href="/" class="btn">Go Back</a>
+  </div>
+</body>
+</html>

templates/results.html

@@ -0,0 +1,185 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <title>Prediction Results</title>
+    <style>
+        body {
+            background-color: #041C32;
+            color: #ECB365;
+            font-family: Arial, sans-serif;
+            margin: 0;
+            padding: 20px;
+        }
+        .container {
+            max-width: 600px;
+            margin: auto;
+            background-color: #04293A;
+            padding: 20px;
+            border-radius: 8px;
+        }
+        h1 {
+            color: #ECB365;
+            text-align: center;
+        }
+        table {
+            width: 100%;
+            border-collapse: collapse;
+            margin-top: 20px;
+        }
+        th, td {
+            border: 1px solid #064663;
+            padding: 10px;
+            text-align: center;
+        }
+        th {
+            background-color: #064663;
+        }
+        .positive {
+            color: green;
+            font-weight: bold;
+        }
+        .negative {
+            color: red;
+            font-weight: bold;
+        }
+        .btn {
+            display: block;
+            margin: 20px auto 0;
+            padding: 10px 15px;
+            background-color: #ECB365;
+            color: #041C32;
+            border: none;
+            border-radius: 4px;
+            text-decoration: none;
+            font-weight: bold;
+            width: fit-content;
+        }
+        /* Tooltip container */
+        .tooltip {
+            position: relative;
+            display: inline-block;
+            cursor: pointer;
+        }
+        /* Tooltip text (info card) */
+        .tooltip .tooltip-content {
+            visibility: hidden;
+            width: 200px;
+            background-color: #ECB365;
+            color: #041C32;
+            text-align: center;
+            border-radius: 6px;
+            padding: 10px;
+            position: absolute;
+            z-index: 1;
+            bottom: 125%;  /* Position above the text */
+            left: 50%;
+            transform: translateX(-50%);
+            opacity: 0;
+            transition: opacity 0.3s;
+        }
+        /* Tooltip arrow */
+        .tooltip .tooltip-content::after {
+            content: "";
+            position: absolute;
+            top: 100%; /* At the bottom of the tooltip */
+            left: 50%;
+            transform: translateX(-50%);
+            border-width: 5px;
+            border-style: solid;
+            border-color: #ECB365 transparent transparent transparent;
+        }
+        /* Show tooltip on hover */
+        .tooltip:hover .tooltip-content {
+            visibility: visible;
+            opacity: 1;
+        }
+    </style>
+</head>
+<body>
+    <div class="container">
+        <h1>Prediction Results</h1>
+        <p>Note: This is a demo model results, so results may vary and be weak on predictions.</p>
+        <table>
+            <tr>
+                <th>Model</th>
+                <th>Predicted Price</th>
+                <th>Difference (Price - EngAmt)</th>
+            </tr>
+            <tr>
+                <td>
+                    <div class="tooltip">
+                        GIA
+                        <div class="tooltip-content">
+                            <strong>Note:</strong> this GIA model is trainned over 372 records.
+                        </div>
+                    </div>
+                </td>
+                <td>{{ gia_price }}</td>
+                <td>
+                    {% if gia_diff >= 0 %}
+                        <span class="positive">{{ gia_diff }}</span>
+                    {% else %}
+                        <span class="negative">{{ gia_diff }}</span>
+                    {% endif %}
+                </td>
+            </tr>
+            <tr>
+                <td>
+                    <div class="tooltip">
+                        Grade
+                        <div class="tooltip-content">
+                            <strong>Note:</strong> this Grade model is trainned over 641 records.
+                        </div>
+                    </div>
+                </td>
+                <td>{{ grade_price }}</td>
+                <td>
+                    {% if grade_diff >= 0 %}
+                        <span class="positive">{{ grade_diff }}</span>
+                    {% else %}
+                        <span class="negative">{{ grade_diff }}</span>
+                    {% endif %}
+                </td>
+            </tr>
+            <tr>
+                <td>
+                    <div class="tooltip">
+                        By Grade
+                        <div class="tooltip-content">
+                            <strong>Note:</strong> this By Grade model is trainned over 641 records.
+                        </div>
+                    </div>
+                </td>
+                <td>{{ bygrade_price }}</td>
+                <td>
+                    {% if bygrade_diff >= 0 %}
+                        <span class="positive">{{ bygrade_diff }}</span>
+                    {% else %}
+                        <span class="negative">{{ bygrade_diff }}</span>
+                    {% endif %}
+                </td>
+            </tr>
+            <tr>
+                <td>
+                    <div class="tooltip">
+                        Makable
+                        <div class="tooltip-content">
+                            <strong>Note:</strong> this Makable model is trainned over 1774 records.
+                        </div>
+                    </div>
+                </td>
+                <td>{{ makable_price }}</td>
+                <td>
+                    {% if makable_diff >= 0 %}
+                        <span class="positive">{{ makable_diff }}</span>
+                    {% else %}
+                        <span class="negative">{{ makable_diff }}</span>
+                    {% endif %}
+                </td>
+            </tr>
+        </table>
+        <a href="{{ url_for('home') }}" class="btn">Make Another Prediction</a>
+    </div>
+</body>
+</html>

utils/tools.py

@@ -0,0 +1,130 @@
+from joblib import dump, load 
+import pandas as pd
+from sklearn import metrics
+from flask import flash
+import numpy as np 
+import pandas as pd 
+from sklearn.preprocessing import LabelEncoder
+from sklearn.metrics.pairwise import cosine_similarity
+from sklearn import metrics
+
+
+def data_similarity(df,pt,index,column,value):
+    # index fetch
+    index = np.where(pt.index==index)[0][0]
+    similarity_scores = cosine_similarity(pt)
+    similar_items = sorted(list(enumerate(similarity_scores[index])),key=lambda x:x[1],reverse=True)[1:2]
+    
+    data = []
+    for i in similar_items:
+        item = []
+        temp_df = df[df['index'] == pt.index[i[0]]]
+        item.extend(list(temp_df.drop_duplicates(index)[value].values))
+        #item.extend(list(temp_df.drop_duplicates(index)[column].values))
+        #item.extend(list(temp_df.drop_duplicates(index)[index].values))
+        
+        data.append(item) 
+    list = [item.item() if isinstance(item, np.generic) else item for sublist in data for item in sublist]
+    
+    original_values = [list['Change_cts_value'].inverse_transform([val]) for val in list]
+    
+    return original_values  
+    
+def recommendation_generator(df):
+    try:
+        pivot_cts = df.pivot_table(index='EngCts', columns='MkblCts', values='Change_cts_value')
+        pivot_shp = df.pivot_table(index='EngShp', columns='MkblShp', values='change_shape_value') 
+        pivot_qua = df.pivot_table(index='EngQua', columns='MkblQua', values='Change_quality_value')
+        pivot_col = df.pivot_table(index='EngCol', columns='MkblCol', values='Change_color_value')
+        pivot_cut = df.pivot_table(index='EngCut', columns='MkblCut', values='Change_cut_value')
+        
+        #==============================================================================
+        # # Recommendation
+        #==============================================================================
+        cts_data = data_similarity(df,pivot_cts,'EngCts','MkblCts','Change_cts_value')
+        shp_data = data_similarity(df,pivot_shp,'EngShp','MkblShp','Change_shape_value')
+        qua_data = data_similarity(df,pivot_qua,'EngQua','MkblQua','Change_quality_value')
+        col_data = data_similarity(df,pivot_col,'EngCol','MkblCol','Change_color_value')
+        cut_data = data_similarity(df,pivot_cut,'EngCut','MkblCut','Change_cut_value')
+              
+        return cts_data,shp_data,qua_data,col_data,cut_data
+    
+    except Exception as e:
+        flash(f'Error generating recommendation: {e}', 'error')
+        return None
+
+def classification_report(df):
+    try:
+        classifcation_data = df[["EngGraphCts","EngCts","EngShp","EngQua","EngCol","EngCut","EngPol","EngSym","EngFlo","EngNts","EngMikly","EngLab","EngAmt",
+                                 "MkblCts","MkblShp","MkblQua","MkblCol","MkblCut","MkblPol","MkblSym","MkblFlo","MkblNts","MkblMikly","MkblLab","MkblAmt"]] 
+        
+        #==============================================================================
+        # # Feature Engineering to generate new columns  
+        #==============================================================================
+        # Make predictions
+        classifcation_data["Cts_diff_eng_mkbl"] = round(classifcation_data["EngCts"] - classifcation_data["MkblCts"],2)
+
+        # Create a new column 'Change_Label' based on the values in 'Cts_diff_eng_mkbl'
+        classifcation_data['Change_cts_value'] = classifcation_data['Cts_diff_eng_mkbl'].apply(
+            lambda x: str(x)+' negative change' if x < 0 else (str(x)+' positive change' if x > 0 else 'no change')
+        )
+        
+        # Create a new column 'Shape_Change' based on the values in 'EngShp' and 'MkblShp'
+        classifcation_data['Change_shape_value'] = classifcation_data.apply(
+            lambda row: str(row['EngShp'])+' to '+str(row['MkblShp'])+' shape change' if row['EngShp'] != row['MkblShp'] else 'shape not change', axis=1
+        )
+        
+        # Create a new column 'quality_Change' based on the values in 'EngQua' and 'MkblQua'
+        classifcation_data['Change_quality_value'] = classifcation_data.apply(
+            lambda row: str(row['EngQua'])+' to '+str(row['MkblQua'])+' quality change' if row['EngQua'] != row['MkblQua'] else 'quality not change', axis=1
+        )
+        
+        # Create a new column 'color_Change' based on the values in 'EngCol' and 'MkblCol'
+        classifcation_data['Change_color_value'] = classifcation_data.apply(
+            lambda row: str(row['EngCol'])+' to '+str(row['MkblCol'])+' color change' if row['EngCol'] != row['MkblCol'] else 'color not change', axis=1
+        )
+        
+        # Create a new column 'cut_Change' based on the values in 'EngCut' and 'MkblCut'
+        classifcation_data['Change_cut_value'] = classifcation_data.apply(
+            lambda row: str(row['EngCut'])+' to '+str(row['MkblCut'])+' cut change' if row['EngCut'] != row['MkblCut'] else 'cut not change', axis=1
+        )
+        
+        #==============================================================================
+        # # Label Encoding and storing the label encoders 
+        #==============================================================================
+        
+        # Get list of categorical variables
+        s = (classifcation_data.dtypes =="object")
+        object_cols = list(s[s].index)
+        print("Categorical variables:")
+        print(object_cols)
+
+        # Make copy to avoid changing original data 
+        label_data = classifcation_data.copy()
+
+        # Apply label encoder to each column with categorical data
+        label_encoder = LabelEncoder()
+        for col in object_cols:
+            label_data[col] = label_encoder.fit_transform(label_data[col])
+            dump(label_encoder, f"./AI_In_Diamond_Industry/Label_encoders/label_encoder_{col}.joblib")   
+                
+        label_data.head()
+        
+        #==============================================================================
+        # # recommendation_system
+        #==============================================================================
+        df=classifcation_data.copy()
+        
+        =recommendation_generator(df)
+        
+        
+        
+        
+        return label_data
+    except Exception as e:
+        flash(f'Error generating classification report: {e}', 'error')
+        return None
+  
+
+    
+