Upload credit scoring app

.gitignore

@@ -0,0 +1,2 @@
+__pycache__
+.venv

.streamlit/config.toml

@@ -0,0 +1,7 @@
+[theme]
+base="light"
+primaryColor="#00052D"
+backgroundColor="#FFFFFF"
+secondaryBackgroundColor="#F4F5F7"
+textColor="#00052D"
+font="sans serif"

README.md

@@ -1,9 +1,11 @@
 ---
-title: Credit Scoring V2
-emoji: 🚀
+title: Credit Scoring
+emoji: 🏆
 colorFrom: yellow
-colorTo: purple
-sdk: static
+colorTo: yellow
+sdk: streamlit
+sdk_version: 1.29
+app_file: app.py
 pinned: false
 license: mit
 ---

app.py

@@ -0,0 +1,409 @@
+# type: ignore -- ignores linting import issues when using multiple virtual environments
+import streamlit.components.v1 as components
+import streamlit as st
+import pandas as pd
+import logging
+from deeploy import Client
+from constants import (
+    relationship_dict,
+    occupation_dict,
+    education_dict,
+    workclass_dict,
+    countries_dict,
+    marital_status_dict,
+)
+
+# reset Plotly theme after streamlit import
+import plotly.io as pio
+
+
+pio.templates.default = "plotly"
+
+logging.basicConfig(level=logging.INFO)
+
+st.set_page_config(layout="wide")
+
+st.title("Credit-Scoring Model Explainability")
+
+st.markdown(
+    """
+    <style>
+        section[data-testid="stSidebar"] {
+            width: 300px !important; # Set the width to your desired value
+        }
+    </style>
+    """,
+    unsafe_allow_html=True,
+)
+
+
+def send_evaluation(
+    client, deployment_id, request_log_id, prediction_log_id, evaluation_input
+):
+    """Send evaluation to Deeploy."""
+    try:
+        with st.spinner("Submitting response..."):
+            # Call the explain endpoint as it also includes the prediction
+            client.evaluate(
+                deployment_id, request_log_id, prediction_log_id, evaluation_input
+            )
+        return True
+    except Exception as e:
+        logging.error(e)
+        st.error(
+            "Failed to submit feedback."
+            + "Check whether you are using the right model URL and Token. "
+            + "Contact Deeploy if the problem persists."
+        )
+        st.write(f"Error message: {e}")
+
+
+def get_model_url():
+    model_url = st.text_area(
+        "Model URL (without the /explain endpoint, default is the demo deployment)",
+        "https://api.app.deeploy.ml/workspaces/708b5808-27af-461a-8ee5-80add68384c7/deployments/dc8c359d-5f61-4107-8b0f-de97ec120289/",
+        height=125,
+    )
+    elems = model_url.split("/")
+    try:
+        workspace_id = elems[4]
+        deployment_id = elems[6]
+    except IndexError:
+        workspace_id = ""
+        deployment_id = ""
+    return model_url, workspace_id, deployment_id
+
+
+def ChangeButtonColour(widget_label, font_color, background_color="transparent"):
+    # func to change button colors
+    htmlstr = f"""
+        <script>
+            var elements = window.parent.document.querySelectorAll('button');
+            for (var i = 0; i < elements.length; ++i) {{ 
+                if (elements[i].innerText == '{widget_label}') {{ 
+                    elements[i].style.color ='{font_color}';
+                    elements[i].style.background = '{background_color}'
+                }}
+            }}
+        </script>
+        """
+    components.html(f"{htmlstr}", height=0, width=0)
+
+
+with st.sidebar:
+    st.image("deeploy_logo_wide.png", width=250)
+
+    # Ask for model URL and token
+    host = st.text_input("Host (Changing is optional)", "app.deeploy.ml")
+    model_url, workspace_id, deployment_id = get_model_url()
+    deployment_token = st.text_input("Deeploy Model Token", "my-secret-token")
+    if deployment_token == "my-secret-token":
+        st.warning("Please enter Deeploy API token.")
+    # Split model URL into workspace and deployment ID
+
+    # st.write("Values below are for debug only:")
+    # st.write("Workspace ID: ", workspace_id)
+    # st.write("Deployment ID: ", deployment_id)
+
+    client_options = {
+        "host": host,
+        "deployment_token": deployment_token,
+        "workspace_id": workspace_id,
+    }
+    client = Client(**client_options)
+
+# with tabs[0] as loan_application:
+selected = "Loan Application"
+# if selected == "Loan Application":
+# Attributes
+st.subheader("Loan Application")
+with st.expander("Application form", expanded=False):
+    # Split view in 2 columns
+    col1, col2 = st.columns(2)
+    with col1:
+        # Create input fields for attributes from constant dicts
+        age = st.number_input("Age", min_value=0, max_value=100, value=30)
+        marital_status = st.selectbox("Marital Status", marital_status_dict.keys())
+        marital_status_id = marital_status_dict[marital_status]
+        native_country = st.selectbox(
+            "Native Country", countries_dict.keys(), index=len(countries_dict) - 1
+        )
+        native_country_id = countries_dict[native_country]
+        relationship = st.selectbox("Relative", relationship_dict.keys(), index=1)
+        relationship_id = relationship_dict[relationship]
+        occupation = st.selectbox("Occupation", occupation_dict.keys(), index=1)
+        occupation_id = occupation_dict[occupation]
+
+    with col2:
+        education = st.selectbox("Education", education_dict.keys(), index=4)
+        education_id = education_dict[education]
+        workclass = st.selectbox("Workclass", workclass_dict.keys())
+        workclass_id = workclass_dict[workclass]
+        hours_per_week = st.number_input(
+            "Hours per week", min_value=0, max_value=100, value=40
+        )
+        capital_gain = st.number_input(
+            "Yearly income [€]", min_value=0, max_value=1000000, value=70000
+        )
+        capital_loss = st.number_input(
+            "Yearly expenditures [€]", min_value=0, max_value=1000000, value=60000
+        )
+    data_df = pd.DataFrame(
+        [
+            [
+                age,
+                workclass,
+                education,
+                marital_status,
+                occupation,
+                relationship,
+                capital_gain,
+                capital_loss,
+                hours_per_week,
+                native_country,
+            ]
+        ],
+        columns=[
+            "Age",
+            "Workclass",
+            "Education",
+            "Marital Status",
+            "Occupation",
+            "Relative",
+            "Yearly Income [€]",
+            "Yearly expenditures [€]",
+            "Hours per week",
+            "Native Country",
+        ],
+    )
+    data_df_t = data_df.T
+    request_body = {
+        "instances": [
+            [
+                age,
+                workclass_id,
+                education_id,
+                marital_status_id,
+                occupation_id,
+                relationship_id,
+                capital_gain,
+                capital_loss,
+                hours_per_week,
+                native_country_id,
+            ]
+        ]
+    }
+if "predict_button_clicked" not in st.session_state:
+    st.session_state.predict_button_clicked = False
+if deployment_token != "my-secret-token":
+    predict_button = st.button(
+        "Predict", key="predict_button", help="Click to get the AI prediction."
+    )
+    if predict_button:
+        st.session_state.predict_button_clicked = True
+        selected = "Loan Decision"
+
+
+if selected == "Loan Decision":
+    # If no prediction, show "loading..."
+    try:
+        with st.spinner("Loading..."):
+            # Call the explain endpoint as it also includes the prediction
+            exp = client.explain(
+                request_body=request_body, deployment_id=deployment_id
+            )
+        # Read explanation to dataframe from json
+        predictions = exp["predictions"]
+        request_log_id = exp["requestLogId"]
+        prediction_log_id = exp["predictionLogIds"][0]
+
+        exp_df = pd.DataFrame(
+            [exp["explanations"][0]["shap_values"]], columns=exp["featureLabels"]
+        )
+
+        exp_df.columns = data_df.columns
+
+        exp_df_t = exp_df.T
+
+        # Merge data and explanation
+        exp_df_t = data_df_t.merge(exp_df_t, left_index=True, right_index=True)
+
+        weight_feat = "Weight"
+        exp_df_t.columns = ["Feature value", weight_feat]
+        exp_df_t["Feature"] = exp_df_t.index
+        exp_df_t = exp_df_t[["Feature", "Feature value", weight_feat]]
+        exp_df_t["Feature value"] = exp_df_t["Feature value"].astype(str)
+        
+        # Filter values below 0.01
+        exp_df_t = exp_df_t[
+            (exp_df_t[weight_feat] > 0.01) | (exp_df_t[weight_feat] < -0.01)
+        ]
+        exp_df_t[weight_feat] = exp_df_t[weight_feat].astype(float).round(2)
+
+        pos_exp_df_t = exp_df_t[exp_df_t[weight_feat] > 0]
+        pos_exp_df_t = pos_exp_df_t.sort_values(by=weight_feat, ascending=False)
+
+        neg_exp_df_t = exp_df_t[exp_df_t[weight_feat] < 0]
+        neg_exp_df_t = neg_exp_df_t.sort_values(by=weight_feat, ascending=True)
+        neg_exp_df_t[weight_feat] = neg_exp_df_t[weight_feat].abs()
+
+        # Get 3 features with highest positive relevance score
+        pos_feats = pos_exp_df_t[weight_feat].nlargest(3).index.tolist()
+        # For feature, get feature value and concatenate into a single string
+        pos_feats = [
+            f"{feat}: {pos_exp_df_t.loc[feat, 'Feature value']}"
+            for feat in pos_feats
+        ]
+        # Get 3 features with highest negative relevance score
+        neg_feats = neg_exp_df_t[weight_feat].nlargest(3).index.tolist()
+        # For feature, get feature value and concatenate into a single string
+        neg_feats = [
+            f"{feat}: {neg_exp_df_t.loc[feat, 'Feature value']}"
+            for feat in neg_feats
+        ]
+
+        if predictions[0]:
+            # Show prediction
+            st.subheader("Loan Decision: :green[POSITIVE]", divider="green")
+            # Format subheader to green
+            st.markdown(
+                "<style>.css-1v3fvcr{color: green;}</style>", unsafe_allow_html=True
+            )
+
+            # If prediction is positive, first show positive features, then negative features
+            st.success(
+                "**Positive credit suitability**. This is primarily attributed to:  \n - "
+                + "  \n- ".join(pos_feats)
+            )
+            st.warning(
+                "However, the following features weight ***against*** the loan application:  \n - "
+                + "  \n- ".join(neg_feats)
+                + "  \n See explanation below for more details.",
+                icon="⚠️",
+            )
+        else:
+            st.subheader("Loan Decision: :red[NEGATIVE]", divider="red")
+            # If prediction is negative, first show negative features, then positive features
+            st.error(
+                "**Negative credit suitability**. This is primarily attributed to:  \n - "
+                + "  \n - ".join(neg_feats)
+                + "."
+            )
+            st.warning(
+                "However, the following factors weigh ***in favor*** of the loan applicant:  \n - "
+                + "  \n - ".join(pos_feats)
+                + ".  \n See below for more details.",
+                icon="⚠️",
+            )
+        explanation_expander = st.expander("Show explanation")
+        with explanation_expander:
+            # Show explanation
+            col_pos, col_neg = st.columns(2)
+
+            with col_pos:
+                st.subheader("Factors :green[in favor] of loan approval")
+                # st.success("**Factors in favor of loan approval**")
+                st.dataframe(
+                    pos_exp_df_t,
+                    hide_index=True,
+                    width=600,
+                    column_config={
+                        "Weight": st.column_config.ProgressColumn(
+                            "Weight",
+                            width="small",
+                            format=" ",
+                            min_value=0,
+                            max_value=1,
+                        )
+                    },
+                )
+
+            with col_neg:
+                st.subheader("Factors :red[against] loan approval")
+                # st.error("**Factors against loan approval**")
+                st.dataframe(
+                    neg_exp_df_t,
+                    hide_index=True,
+                    width=600,
+                    column_config={
+                        "Weight": st.column_config.ProgressColumn(
+                            "Weight",
+                            width="small",
+                            format=" ",
+                            min_value=0,
+                            max_value=1,
+                        )
+                    },
+                )
+
+        st.divider()
+        
+        # Add prediction evaluation
+        st.subheader("Prediction Evaluation: Do you agree with the AI prediction?")
+        st.info(
+            "AI model predictions always come with a certain level of uncertainty. Evaluate the correctness of the prediction based on your expertise and experience."
+        )
+        cols = st.columns(4)
+        col_yes, col_no = cols[:2]
+        with col_yes:
+            yes_button = st.button(
+                "Yes, I agree",
+                key="yes_button",
+                use_container_width=True,
+                help="Click if you agree with the prediction",
+            )
+            ChangeButtonColour("Yes, I agree", "white", "green")
+        with col_no:
+            no_button = st.button(
+                "No, I disagree",
+                key="no_button",
+                use_container_width=True,
+                help="Click if you disagree with the prediction",
+                type="primary",
+            )
+            ChangeButtonColour("No, I disagree", "white", "#DD360C")
+            # ChangeButtonColour("No, I disagree", "#DD360C", "#F0F0F0")
+        if "eval_selected" not in st.session_state:
+            st.session_state["eval_selected"] = False
+        if yes_button:
+            st.session_state.eval_selected = True
+            st.session_state.evaluation_input = {
+                "result": 0  # Agree with the prediction
+            }
+        if no_button:
+            st.session_state.eval_selected = True
+            desired_output = not predictions[0]
+            st.session_state.evaluation_input = {
+                "result": 1,  # Disagree with the prediction
+                "value": {"predictions": [desired_output]},
+            }
+
+        success = False
+        if st.session_state.eval_selected:
+            comment = st.text_input("Would you like to add a comment?")
+            if comment:
+                st.session_state.evaluation_input["explanation"] = comment
+            logging.debug(
+                "Selected feedback:" + str(st.session_state.evaluation_input)
+            )
+            if st.button("Submit", key="submit_button"):
+                st.session_state.eval_selected = False
+                success = send_evaluation(
+                    client,
+                    deployment_id,
+                    request_log_id,
+                    prediction_log_id,
+                    st.session_state.evaluation_input,
+                )
+        if success:
+            st.session_state.eval_selected = False
+            st.success("Feedback submitted successfully.")
+
+    except Exception as e:
+        logging.error(e)
+        st.error(
+            "Failed to retrieve the prediction or explanation."
+            + "Check whether you are using the right model URL and Token. "
+            + "Contact Deeploy if the problem persists."
+        )
+        # st.write(f"Error message: {e}")

constants.py

@@ -0,0 +1,109 @@
+countries_dict = {
+    "United-States": 0,
+    "Cambodia": 1,
+    "England": 2,
+    "Puerto-Rico": 3,
+    "Canada": 4,
+    "Germany": 5,
+    "Outlying-US (Guam - USVI - etc.)": 6,
+    "India": 7,
+    "Japan": 8,
+    "Greece": 9,
+    "South": 10,
+    "China": 11,
+    "Cuba": 12,
+    "Iran": 13,
+    "Honduras": 14,
+    "Philippines": 15,
+    "Italy": 16,
+    "Poland": 17,
+    "Jamaica": 18,
+    "Vietnam": 19,
+    "Mexico": 20,
+    "Portugal": 21,
+    "Ireland": 22,
+    "France": 23,
+    "Dominican Republic": 24,
+    "Laos": 25,
+    "Ecuador": 26,
+    "Taiwan": 27,
+    "Haiti": 28,
+    "Columbia": 29,
+    "Hungary": 30,
+    "Guatemala": 31,
+    "Nicaragua": 32,
+    "Scotland": 33,
+    "Thailand": 34,
+    "Yugoslavia": 35,
+    "El Salvador": 36,
+    "Trinadad & Tobago": 37,
+    "Peru": 38,
+    "Hong": 39,
+    "Holland - Netherlands": 40,
+}
+
+relationship_dict = {
+    "Unmarried": 5,
+    "Not in Family": 3,
+    "Wife": 0,
+    "Own child": 1,
+    "Husband": 2,
+    "Other Relative": 4,
+}
+
+occupation_dict = {
+    "Prof Specialty": 5,
+    "Tech Support": 0,
+    "Craft Repair": 1,
+    "Other Service": 2,
+    "Sales": 3,
+    "Executive Managerial": 4,
+    "Handlers Cleaners": 6,
+    "Machine Op Inspect": 7,
+    "Adm Clerical": 8,
+    "Farming Fishing": 9,
+    "Transport Moving": 10,
+    "Priv House Serv": 11,
+    "Protective Serv": 12,
+    "Armed Forces": 13,
+}
+
+education_dict = {
+    "Associate Academic": 5,
+    "Associate Vocational": 6,
+    "Prof School": 4,
+    "Doctorate": 13,
+    "Masters": 10,
+    "Bachelors": 0,
+    "Some College": 1,
+    "High School Graduate": 3,
+    "12th Grade": 9,
+    "11th Grade": 2,
+    "10th Grade": 12,
+    "9th Grade": 7,
+    "7th-8th Grade": 8,
+    "5th-6th Grade": 14,
+    "1st-4th Grade": 11,
+    "Preschool": 15,
+}
+
+workclass_dict = {
+    "Private": 0,
+    "Self Employed Not Incorporated": 1,
+    "Self Employed Incorporated": 2,
+    "Federal Government": 3,
+    "Local Government": 4,
+    "State Government": 5,
+    "Without Pay": 6,
+    "Never Worked": 7,
+}
+
+marital_status_dict = {
+    "Never-married": 2,
+    "Married-civ-spouse": 0,
+    "Divorced": 1,
+    "Separated": 3,
+    "Widowed": 4,
+    "Married-spouse-absent": 5,
+    "Married-AF-spouse": 6,
+}

pyproject.toml

@@ -0,0 +1,23 @@
+[tool.poetry]
+name = "credit-scoring"
+version = "0.1.0"
+description = ""
+authors = ["Adam Dubowski <[email protected]>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = ">=3.8, !=3.9.7, <3.11" # Required to avoid conflicts with numpy, scipy and streamlit
+scikit-learn = "1.3.0"
+shap = "0.42.0"
+dill = "0.3.6"
+matplotlib = "3.7.0"
+boto3 = "1.28.0"
+joblib = "1.3.2"
+scipy = "1.10.1"
+plotly = "5.18.0"
+watchdog = "3.0.0"
+streamlit = "1.29.0"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

requirements.txt

@@ -0,0 +1,12 @@
+scikit-learn==1.3.0
+shap==0.42.0
+dill==0.3.6
+matplotlib==3.7.0
+boto3==1.28.0
+joblib==1.3.2
+streamlit==1.29
+scipy==1.10.1
+shap==0.42.0
+plotly==5.18.0
+watchdog==3.0.0
+deeploy==1.2.1

style.css

@@ -1,28 +0,0 @@
-body {
-	padding: 2rem;
-	font-family: -apple-system, BlinkMacSystemFont, "Arial", sans-serif;
-}
-
-h1 {
-	font-size: 16px;
-	margin-top: 0;
-}
-
-p {
-	color: rgb(107, 114, 128);
-	font-size: 15px;
-	margin-bottom: 10px;
-	margin-top: 5px;
-}
-
-.card {
-	max-width: 620px;
-	margin: 0 auto;
-	padding: 16px;
-	border: 1px solid lightgray;
-	border-radius: 16px;
-}
-
-.card p:last-child {
-	margin-bottom: 0;
-}