%%writefile app.py import streamlit as st import pandas as pd import io import joblib…
- User
%%writefile app.py import streamlit as st import pandas as pd import io import joblib import base64 import matplotlib.pyplot as plt import seaborn as sns import datetime from sklearn import tree from sklearn.tree import _tree import numpy as np
Function to upload and generate predictions
def upload_and_generate_predictions(): # File upload and prediction code def get_base64(bin_file): with open(bin_file, "rb") as f: data = f.read() return base64.b64encode(data).decode()
def set_background(png_file): bin_str = get_base64(png_file) page_bg_img = ( """ <style> .stApp { background-image: url("data:image/png;base64,%s"); background-size: cover; } </style> """ % bin_str ) st.markdown(page_bg_img, unsafe_allow_html=True) set_background("Screenshot (29).png") red_title = '<h1 style="color: white;">Equipment Failure Prediction</h1>' # Display the red title using st.markdown st.markdown(red_title, unsafe_allow_html=True) # Display the custom CSS style uploaded_file = st.file_uploader( "Upload an Excel or CSV file", type=["xlsx", "csv"] ) if uploaded_file is not None: # Read the file into a DataFrame if ( uploaded_file.type == "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet" ): # Excel file df = pd.read_excel(uploaded_file, engine="openpyxl") else: # CSV file df = pd.read_csv(uploaded_file) # st.session_state.predictions_df = df # st.session_state.uploaded_file=uploaded_file # Display the first screen if st.button("Generate predictions"): model = joblib.load("des_tree_clss.joblib") prediction = "" if "machine_status" in df.columns.to_list(): prediction = model.predict(df.drop(columns=["machine_status"])) else: prediction = model.predict(df) df["Predicted_Status"] = prediction st.success("Predictions made successfully!") st.session_state.predictions_df = df st.session_state.uploaded_file = uploaded_file # Display the modified DataFrame with predictions # Save the DataFrame with predictions to st.session_state # Move to the second screen (graph display)def display_graph(predictions_df, uploaded_file): def get_base64(bin_file): with open(bin_file, "rb") as f: data = f.read() return base64.b64encode(data).decode()
def set_background(png_file): bin_str = get_base64(png_file) page_bg_img = ( """ <style> .stApp { background-image: url("data:image/png;base64,%s"); background-size: cover; } </style> """ % bin_str ) st.markdown(page_bg_img, unsafe_allow_html=True) set_background("Screenshot (32).png") st.markdown('<div style="margin-top: 50px;"></div>', unsafe_allow_html=True) st.subheader("Early warning Signal:") # Create a DataFrame with the first 10 records with prediction status 1 df_status_1 = predictions_df[predictions_df["Predicted_Status"] == 1].head(10) # Create a DataFrame with all records with prediction status 0 df_status_0 = predictions_df[predictions_df["Predicted_Status"] == 0].head(10) # Combine the DataFrames df_combined = pd.concat([df_status_0, df_status_1]) start_timestamp = datetime.datetime(2023, 1, 1) df_combined["Synthetic_Timestamp"] = pd.date_range( start=start_timestamp, periods=len(df_combined), freq="T" ) # df_combined['Synthetic_Timestamp'] = pd.date_range(start='2023-01-01', periods=len(df_combined), freq='T') plt.figure(figsize=(10, 3)) sns.scatterplot( x="Synthetic_Timestamp", y="Predicted_Status", hue="Predicted_Status", marker="o", s=200, data=df_combined, palette={1: "red", 0: "green"}, ) plt.xticks(rotation=45, ha="right") # plt.title("Machine Status Prediction - Combined") plt.xlabel("Timestamp") plt.ylabel("Value") st.pyplot() # Create a download link st.subheader("Download the File with Predictions:") st.write("Download the File with Predictions:") # st.markdown(title1, unsafe_allow_html=True) modified_file_name = ( f"file_with_predictions_{uploaded_file.name}" if uploaded_file.name else "file_with_predictions.xlsx" ) # Convert DataFrame to binary stream modified_file = io.BytesIO() if ( uploaded_file.type == "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet" ): # Excel file predictions_df.to_excel(modified_file, index=False, engine="xlsxwriter") else: # CSV file predictions_df.to_csv(modified_file, index=False) modified_file.seek(0) # Create a download link st.download_button( label="Download File with Predictions", data=modified_file, file_name=modified_file_name, key="download_file_with_predictions", ) # Rules functions def get_rules(tree, feature_names, class_names): tree_ = tree.tree_ feature_name = [ feature_names[i] if i != _tree.TREE_UNDEFINED else "undefined!" for i in tree_.feature ] paths = [] path = [] def recurse(node, path, paths): if tree_.feature[node] != _tree.TREE_UNDEFINED: name = feature_name[node] threshold = tree_.threshold[node] p1, p2 = list(path), list(path) p1 += [f"({name} <= {np.round(threshold, 3)})"] recurse(tree_.children_left[node], p1, paths) p2 += [f"({name} > {np.round(threshold, 3)})"] recurse(tree_.children_right[node], p2, paths) else: path += [(tree_.value[node], tree_.n_node_samples[node])] paths += [path] recurse(0, path, paths) # sort by samples count samples_count = [p[-1][1] for p in paths] ii = list(np.argsort(samples_count)) paths = [paths[i] for i in reversed(ii)] rules = [] for path in paths: rule = "if " for p in path[:-1]: if rule != "if ": rule += " and " rule += str(p) rule += " then " if class_names is None: rule += "response: " + str(np.round(path[-1][0][0][0], 3)) else: classes = path[-1][0][0] l = np.argmax(classes) rule += f"class: {class_names[l]} (proba: {np.round(100.0*classes[l]/np.sum(classes),2)}%)" rule += f" | based on {path[-1][1]:,} samples" rules += [rule] return rules st.subheader("Model Explainability:") model = joblib.load("des_tree_clss.joblib") rules = get_rules(model, predictions_df.columns, range(2)) table_list = [] for r in rules: colon_split = r.split(":") col_1 = colon_split[0] pipe_split = str(colon_split[1] + colon_split[2]).split("|") # print(colon_split) # print(pipe_split) col_2 = pipe_split[0] col_3 = pipe_split[1] table_list.append([col_1, col_2, col_3]) table_df = pd.DataFrame( table_list, columns=["rule_details", "class_probabilities", "samples_count"] ) rules_data_file = io.BytesIO() table_df.to_csv(rules_data_file, index=False) rules_data_file.seek(0) # Create a download link st.download_button( label="Model Explainability", data=rules_data_file, file_name="rules_data.csv", key="download_rules_data", )Run the app
if name == "main": st.set_option("deprecation.showPyplotGlobalUse", False) st.set_page_config(page_title="Equipment Failure Prediction", page_icon="📈") pages = ["Upload and Predict", "Graph and Download"] page = st.sidebar.selectbox("Select a page", pages) if page == "Upload and Predict": upload_and_generate_predictions() elif page == "Graph and Download": if hasattr(st.session_state, "predictions_df"): display_graph( st.session_state.predictions_df, st.session_state.uploaded_file ) else: st.warning("Please upload a file on the 'Upload and Predict' page first.") this is mu code inthis i have a scatterplot graph i want to modify the code in a way that draw ploltly graph usw click events of ploltly when i click the instance of the circle it should give descion rule for the instance using lime.after graph if i click one circle or instance lime table and rule list should print there it self you can add download predictions and model explananbility in new side bar
Assistant
To modify your code to use Plotly with click events and display LIME (Local Interpretable Model-Agnostic Explanations) tables, you'll need to make several changes. Below is an example of how you might implement this using Plotly.js and LIME for scikit-learn.
Please note that this is a simplified example and may need to be adapted to your specific dataset and model. The LIME package is used to explain the predictions of your model, and Plotly.js is used to create the interactive scatterplot with click events.
First, you'll need to install the necessary packages if you haven't already:
pip install plotly lime[scikit-learn]Here's an example of how you might modify your code to achieve the desired functionality:
import streamlit as st import pandas as pd import io import joblib import base64 import matplotlib.pyplot as plt import seaborn as sns import datetime from sklearn import tree from sklearn.tree import _tree import numpy as np import plotly.express as px import lime from lime.lime_tabular import LimeTabularExplainer # Function to upload and generate predictions def upload_and_generate_predictions(): # ... your existing code ... # Model prediction and data preprocessing if "machine_status" in df.columns.to_list(): prediction = model.predict(df.drop(columns=["machine_status"])) else: prediction = model.predict(df) df["Predicted_Status"] = prediction st.success("Predictions made successfully!") st.session_state.predictions_df = df st.session_state.uploaded_file = uploaded_file # Plotting with Plotly fig = px.scatter(df, x="Synthetic_Timestamp", y="Predicted_Status", color="Predicted_Status") fig.update_traces(marker_size=10) fig.update_layout( xaxis_title="Timestamp", yaxis_title="Value",
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.