Create app.py

app.py

@@ -0,0 +1,133 @@
+import streamlit as st
+import numpy as np
+import pandas as pd
+import pickle
+from copy import deepcopy as dc
+from tensorflow.keras.models import load_model
+
+st.title('Estimate BHP')
+st.subheader("Upload your CSV file here")
+
+# Required columns for file validation
+required_columns = ['PRODUCTION DATE', 'Qliquid', 'GOR', 'Pwh', 'THT', 'WCT']
+
+# File uploader
+uploaded_file = st.file_uploader("Choose a file")
+
+def prepare_dataframe_for_lstm(df, n_steps):
+    df = dc(df)
+    df.set_index('PRODUCTION DATE', inplace=True)
+ 
+    for i in range(1, n_steps + 1):
+        df[f'Qliquid(t-{i})'] = df['Qliquid'].shift(i)
+        df[f'GOR(t-{i})'] = df['GOR'].shift(i)
+        df[f'Pwh(t-{i})'] = df['Pwh'].shift(i)
+        df[f'THT(t-{i})'] = df['THT'].shift(i)
+        df[f'WCT(t-{i})'] = df['WCT'].shift(i)
+ 
+    df.dropna(inplace=True)
+    return df
+ 
+# File processing and validation
+if uploaded_file is not None:
+    try:
+        dataframe = pd.read_csv(uploaded_file)
+        missing_columns = [col for col in required_columns if col not in dataframe.columns]
+ 
+        if missing_columns:
+            st.error(f"The uploaded file is missing the following required columns: {', '.join(missing_columns)}")
+            st.image("description.jpg", caption="Please check that the uploaded file has this structure")
+        else:
+            original_dataframe = dataframe.copy()
+            processed_dataframe = prepare_dataframe_for_lstm(dataframe, 2)
+            st.success("File successfully uploaded and verified!")
+            st.write("Processed Data Preview:", processed_dataframe)
+            st.session_state['processed_dataframe'] = processed_dataframe
+            st.session_state['original_dataframe'] = original_dataframe
+    except Exception as e:
+        st.error(f"An error occurred while processing the file: {e}")
+ 
+# Sidebar for model selection
+model_files = {
+    'modelJ05': 'modelXAMATR_MODELTRAINFILEBETASF.pkl',
+    'modelJ57': 'model57 (2).pkl',
+    'modelJ61': 'modelJ61.pkl',
+    'modelJ68': 'modelJ68.pkl'
+}
+
+selected_model = st.sidebar.selectbox("Select Model", list(model_files.keys()))
+
+# Sidebar for trend selection
+if 'original_dataframe' in st.session_state:
+    available_columns = [col for col in st.session_state['original_dataframe'].columns 
+                        if col not in ['PRODUCTION DATE', 'MBHFP']]
+    selected_trends = st.sidebar.multiselect("Select Trends to Display", available_columns)
+
+# Load the saved model and scaler
+def load_model_m(model_file):
+    with open(model_file, 'rb') as file:
+        data = pickle.load(file)
+    return data
+ 
+data = load_model_m(model_files[selected_model])
+model = data['model']
+scaler = data['scaler']
+ 
+
+def start_prediction():
+    if 'processed_dataframe' in st.session_state:
+        df = st.session_state['processed_dataframe']
+ 
+        # Columns to scale
+        columns_to_scale = ['MBHFP', 'Qliquid', 'GOR', 'Pwh', 'THT', 'WCT', 
+                            'Qliquid(t-1)', 'GOR(t-1)', 'Pwh(t-1)', 'THT(t-1)', 'WCT(t-1)', 
+                            'Qliquid(t-2)', 'GOR(t-2)', 'Pwh(t-2)', 'THT(t-2)', 'WCT(t-2)']
+ 
+        scaled_columns = [col for col in columns_to_scale if col in df.columns]
+        data_predicted = scaler.transform(df[scaled_columns])
+        scaled_df = pd.DataFrame(data_predicted, columns=scaled_columns)
+ 
+        X = scaled_df[['Qliquid', 'GOR', 'Pwh','WCT', 'THT','Qliquid(t-1)','GOR(t-1)','Pwh(t-1)','WCT(t-1)','THT(t-1)','Qliquid(t-2)','GOR(t-2)','Pwh(t-2)','WCT(t-1)','THT(t-2)']]
+        X = X.values.reshape((scaled_df.shape[0], 5, 3))
+        y_pred = model.predict(X).reshape(1,-1)
+        data_predicted[:, 0] = y_pred
+        unscaled_data = scaler.inverse_transform(data_predicted)
+        unscaled_df = pd.DataFrame(unscaled_data, columns=scaled_columns)
+        st.session_state['prediction_result'] = unscaled_df['MBHFP'].values
+    else:
+        st.error("Please upload a file and preprocess it first.")
+ 
+if st.button("Predict"):
+    start_prediction()
+ 
+if 'prediction_result' in st.session_state:
+    st.subheader("Prediction Result:")
+    
+    # Show predictions as a table
+    predictions_table = pd.DataFrame({
+        'Prediction Index': range(len(st.session_state['prediction_result'])),
+        'Predicted BHP': st.session_state['prediction_result']
+    })
+    st.write(predictions_table)
+    
+    # Create simple index-based DataFrame for plotting
+    plot_df = pd.DataFrame({
+        'Predicted BHP': st.session_state['prediction_result']
+    })
+    
+    # Add selected trends, skipping first 2 elements
+    if 'original_dataframe' in st.session_state and selected_trends:
+        original_df = st.session_state['original_dataframe']
+        start_idx = 2  # Skip first 2 elements
+        end_idx = start_idx + len(plot_df)
+        
+        for trend in selected_trends:
+            plot_df[trend] = original_df[trend].iloc[start_idx:end_idx].values
+    
+    # Plot with simple numeric index
+    st.subheader("Visualization")
+    st.line_chart(plot_df)
+    
+    if st.checkbox("Normalize data for better comparison"):
+        normalized_df = (plot_df - plot_df.mean()) / plot_df.std()
+        st.line_chart(normalized_df)