import os import evalml import pandas as pd import streamlit as st import plotly.graph_objects as go from evalml.automl import AutoMLSearch from evalml.data_checks import DefaultDataChecks from streamlit_option_menu import option_menu from evalml.problem_types import detect_problem_type from evalml.automl import get_default_primary_search_objective from evalml.objectives import get_optimization_objectives from time_series_splitter import split_time_series_data from evalml.automl import get_default_primary_search_objective from evalml.objectives import get_optimization_objectives from evalml.model_understanding.metrics import confusion_matrix from evalml.model_understanding.prediction_explanations import explain_predictions from evalml.model_understanding import graph_prediction_vs_actual_over_time st.set_page_config(None,layout="wide") st.title("All_in_one_Model") problem_types = ['BINARY', 'MULTICLASS', 'REGRESSION',] time_problems = ['TIME SERIES REGRESSION','TIME SERIES BINARY', 'TIME SERIES MULTICLASS'] prob = option_menu(None, options=["General Problem","Time Series Problem"], menu_icon="cast", default_index=0, orientation="horizontal",) uploaded_file = st.file_uploader("Upload a CSV file", type=["csv"]) if prob =="General Problem": if uploaded_file is not None: df = pd.read_csv(uploaded_file) with st.container(): col1 ,col2 ,col3 = st.columns(3) with col1: y_col = st.selectbox("Select Output Columns",options=df.columns,index= (df.shape[1])-1,) X = df.drop(y_col,axis=1) y= df[y_col] with col2: detect_prob_type = detect_problem_type(y).name problem_type = st.selectbox("Select Problem Type",options=problem_types,index= problem_types.index(detect_prob_type),) with col3: objective_auto = get_default_primary_search_objective(problem_type).name objectives = [] for objective in get_optimization_objectives(problem_type): objectives.append(objective.name) objective_type = st.selectbox("Select Objective Type",options=objectives,index=objectives.index(objective_auto)) data_checks = DefaultDataChecks(problem_type, objective_type) check = data_checks.validate(X,y) if uploaded_file is not None: if len(check) == 0: st.success("Data Check Successful") else: st.error("Data Check Unsuccessful") X_train, X_test, y_train, y_test = evalml.preprocessing.split_data(X, y, problem_type=problem_type, test_size=0.2,) automl = AutoMLSearch(X_train=X_train, y_train=y_train, X_holdout=X_test, y_holdout=y_test, problem_type=problem_type, allow_long_running_models=False, objective=objective_type, max_batches=3, ensembling=True, verbose=True ) selected = option_menu(None, options=["Home", "Predict","Model_info","Graphs","XAI"], icons=['house', 'person',"card-text", "list-task", 'chat-left-text-fill'], menu_icon="cast", default_index=0, orientation="horizontal",) if selected == "Home": train = st.button("Train Model ") if train: st.write("Training Model ....") automl.search() best_pipeline = automl.best_pipeline best_pipeline.save("best_model.pkl") load_model=automl.load('best_model.pkl') st.dataframe(automl.rankings) y_pred = load_model.predict(X_test) st.write(load_model.score(X_test, y_test, objectives=objectives)) try: y_pred = load_model.predict(X_test) st.dataframe(confusion_matrix(y_test, y_pred)) except: pass if selected =="Predict": try: load_model=automl.load('best_model.pkl') df1= df.drop(y_col,axis=1) column_names = df1.columns column_data_types = df1.dtypes st.subheader("Enter Data:") col1, col2 = st.columns(2) new_row_data = {} for col_name, col_type in zip(column_names, column_data_types): if col_type == 'object': with col1: input_data = st.text_input(f"Enter {col_name}") elif col_type == 'int64' or col_type == 'float64': with col2: input_data = st.number_input(f"Enter {col_name}") else: input_data = None st.write(f"Data type {col_type} not supported for column {col_name}") new_row_data[col_name] = input_data if st.button("Predict"): load_model=automl.load('best_model.pkl') new_df = pd.DataFrame([new_row_data],columns=column_names) st.dataframe(new_df,hide_index=True,width=1200) pred = load_model.predict(new_df) st.success(f"Predicted Value : {pred.values[0]}") except: st.write("Please Train Model first ..") if selected == "Model_info": try: load_model=automl.load('best_model.pkl') st.write(load_model.describe(return_dict=True)) except: st.write("Please Train Model first ..") if selected == "Graphs": try: pass except: st.write("Please Train Model first ..") if selected == "XAI": try: with st.container(): col1 ,col2 = st.columns(2) with col1: load_model=automl.load('best_model.pkl') st.dataframe(load_model.feature_importance) with col2: table = explain_predictions( pipeline=load_model, input_features=X_test, y=None, output_format="dataframe", indices_to_explain=[3], top_k_features=8, include_explainer_values=True, algorithm='shap' ) st.subheader("Positive and Negative contributing features") st.dataframe(table) except: st.write("Please Train Model first ..") try: with open("best_model.pkl", "rb") as f: file_contents = f.read() st.download_button('Download Model', file_contents, file_name='best_model.pkl', mime='application/octet-stream') except: pass if prob == "Time Series Problem": if uploaded_file is not None: df = pd.read_csv(uploaded_file) with st.container(): col1 ,col4,col2 ,col3 = st.columns(4) with col1: y_col = st.selectbox("Select Output Column",options=df.columns,index= (df.shape[1])-1,) X = df.drop(y_col,axis=1) y= df[y_col] with col4: def date_column_name(X): date_column = None for column in X.columns: if pd.api.types.is_datetime64_any_dtype(X[column]): date_column = column break if date_column is None: raise ValueError("No datetime column found in the DataFrame.") return date_column try: pred_date = date_column_name(df) except: pred_date = df.columns[0] date_col = st.selectbox("Select Date Column",options=X.columns,index=X.columns.get_loc(pred_date)) df[date_col] = pd.to_datetime(df[date_col]) with col2: detect_prob_type = detect_problem_type(y).name try: problem_type = st.selectbox("Select Problem Type",options=time_problems,index= time_problems.index(detect_prob_type),) except: problem_type = st.selectbox("Select Problem Type",options=time_problems,index= 0,) with col3: objective_auto = get_default_primary_search_objective(problem_type).name objectives = [] for objective in get_optimization_objectives(problem_type): objectives.append(objective.name) objective_type = st.selectbox("Select Objective Type",options=objectives,index=objectives.index(objective_auto)) X_train, X_test, y_train, y_test = split_time_series_data(date_col,X,y,test_size=0.1) with st.container(): col1 ,col2 ,col3= st.columns(3) with col1: gap = st.number_input('Select Gap in Data ',value= 0,min_value=0,max_value=10) with col2: max_delay = st.number_input('Select Max Delay',value=7,min_value=3,) with col3: forecast_horizon = st.number_input('Select forecast horizon ',value=7) if problem_type=='TIME SERIES REGRESSION': algo_families =["All Algorithm",'RANDOM_FOREST','XGBOOST','LIGHTGBM','LINEAR_MODEL','EXPONENTIAL_SMOOTHING','ARIMA','PROPHET',] elif problem_type=='TIME SERIES BINARY': algo_families =["All Algorithm",'RANDOM_FOREST','XGBOOST','LIGHTGBM','LINEAR_MODEL',"EXTRA_TREES"] elif problem_type=='TIME SERIES MULTICLASS': algo_families =["All Algorithm",'RANDOM_FOREST','XGBOOST','LIGHTGBM','LINEAR_MODEL',"EXTRA_TREES"] algo_select = st.multiselect( 'Select Algorithm', algo_families, default=["All Algorithm"], ) if "All Algorithm" in algo_select or len(algo_select)==0: algo_select=None problem_config = {"gap": gap, "max_delay": max_delay, "forecast_horizon": forecast_horizon, "time_index":date_col } automl_time = AutoMLSearch( X_train, y_train, problem_type = problem_type, objective=objective_type, max_batches=1, ensembling=True, problem_configuration=problem_config, automl_algorithm="iterative", allowed_model_families=algo_select ) with st.container(): col1 ,col2 ,col3= st.columns([3,3,6]) with col1: train_time = st.button("Train Time Series Model....") with col2: load_time = st.button("Load Best Time Series Model....") if train_time: st.write("Model Training.....") automl_time.search() st.dataframe(automl_time.rankings) best_pipeline_time = automl_time.best_pipeline best_pipeline_time.save("best_model_time.pkl") if load_time: try: load_model_time=automl_time.load('best_model_time.pkl') st.write(load_model_time.describe(return_dict=True)) load_model_time.fit(X_train, y_train) best_pipeline_score = load_model_time.score(X_test, y_test, [objective_type], X_train, y_train)[ objective_type] st.write(f"{objective_type} : {best_pipeline_score}") fig = graph_prediction_vs_actual_over_time(load_model_time, X_test, y_test, X_train, y_train, dates=X_test[date_col]) fig.update_layout(height=700) st.plotly_chart(fig,use_container_width=True,height=200) st.header("Predict Next 7 Days") load_model_time.fit(X, y) X_forecast_dates = load_model_time.get_forecast_period(X=X).to_frame() y_forecast = load_model_time.get_forecast_predictions(X=X, y=y) res = load_model_time.get_prediction_intervals(X=pd.DataFrame(X_forecast_dates), y=y_forecast, X_train=X, y_train=y) y_lower = res["0.95_lower"] y_upper = res["0.95_upper"] X_before = X[-31:] y_before = y[-31:] fig2 = go.Figure( [ go.Scatter(x=X_before[date_col], y=y_before, name="Training Data", mode="lines"), go.Scatter( x=X_forecast_dates[date_col], y=y_forecast, name="Forecast Data", mode="lines" ), go.Scatter( x=pd.concat([X_forecast_dates[date_col], X_forecast_dates[date_col][::-1]]), y=pd.concat([y_upper, y_lower[::-1]]), fill="toself", fillcolor="rgba(255,0,0,0.2)", line=dict(color="rgba(255,0,0,0.2)"), name="Forecast Prediction Intervals", showlegend=True, ), ], layout={ "title": "Plot of Last Two Weeks of Data + Forecast Data With Prediction Intervals", "xaxis": dict(title=date_col), "yaxis": dict(title=y_col), }, ) fig2.update_layout(height=600) st.plotly_chart(fig2,use_container_width=True) except: st.write("Please Train Model First....") try: with open("best_model_time.pkl", "rb") as f: file_contents = f.read() st.download_button('Download Model', file_contents, file_name='best_model_time.pkl', mime='application/octet-stream') except: pass file_path = os.path.join('best_model.pkl') file_path2 = os.path.join('best_model_time.pkl') if uploaded_file == None: try: if prob == "General Problem": os.remove(file_path) elif prob == "Time Series Problem": os.remove(file_path2) except: pass