Added files

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

app.py

@@ -0,0 +1,210 @@
+import streamlit as st
+import pandas as pd
+import pickle
+import numpy as np
+import os
+from openai import OpenAI
+import utils as ut
+
+if "GROQ_API_KEY" in os.environ:
+    api_key = os.environ.get("GROQ_API_KEY")
+else:
+    api_key = st.secrets["GROQ_API_KEY"]
+    
+client = OpenAI(
+    base_url="https://api.groq.com/openai/v1",
+    api_key=api_key
+)
+
+def load_model(file_name):
+    with open(file_name, 'rb') as file:
+        return pickle.load(file)
+    
+xgb_model = load_model('xgb_model.pkl')
+naive_bayes_model = load_model('nb_model.pkl')
+random_forest_model = load_model('rf_model.pkl')
+decision_tree_model = load_model('dt_model.pkl')
+knn_model = load_model('knn_model.pkl')
+
+def prepare_input_data(credit_score, location, gender, age, tenure, balance, num_products, has_credit_card, is_active_member, estimated_salary):
+    input_dict = {
+        'CreditScore': credit_score,
+        'Age': age,
+        'Tenure': tenure,
+        'Balance': balance,
+        'NumOfProducts': num_products,
+        'HasCrCard': has_credit_card,
+        'IsActiveMember': is_active_member,
+        'EstimatedSalary': estimated_salary,
+        'Geography_France': 1 if location == 'France' else 0,
+        'Geography_Germany': 1 if location == 'Germany' else 0,
+        'Geography_Spain': 1 if location == 'Spain' else 0,
+        'Gender_Male': 1 if gender == 'Male' else 0,
+        'Gender_Female': 1 if gender == 'Female' else 0
+    }
+
+    input_df = pd.DataFrame([input_dict])
+    return input_df, input_dict
+
+def make_prediction(input_df, input_dict):
+    probabilities = {
+        'XGBoost': xgb_model.predict_proba(input_df)[0, 1],
+        'Naive Bayes': naive_bayes_model.predict_proba(input_df)[0, 1],
+        'Random Forest': random_forest_model.predict_proba(input_df)[0, 1],
+        'Decision Tree': decision_tree_model.predict_proba(input_df)[0, 1],
+        'K-Nearest Neighbors': knn_model.predict_proba(input_df)[0, 1],
+    }
+    avg_probability = np.mean(list(probabilities.values()))
+
+    col1, col2 = st.columns(2)
+
+    with col1:
+        fig = ut.create_guage_chart(avg_probability)
+        st.plotly_chart(fig, use_container_width=True)
+        st.write(f"The customer has a {avg_probability:.2f}% probability of churning.")
+
+    with col2:
+        fig = ut.create_model_probability_chart(probabilities)
+        st.plotly_chart(fig, use_container_width=True)
+
+    st.markdown("### Model Probabilities")
+    for model, prob in probabilities.items():
+        st.markdown(f"{model}: {prob:.2f}")
+
+    st.markdown(f"### Average Probability: {avg_probability:.2f}")
+
+    return avg_probability
+
+def explain_prediction(probability, input_dict, surname):
+    prompt = f"""You are an expert data scientist at a bank, where you specialize in interpreting and explaining predictions of machine learning models.
+
+A customer with the name {surname} has been assessed as having a {round(probability * 100, 1)}% likelihood of churning based on their profile and engagement. Here is the customer's information:
+
+{input_dict}
+
+Here are the machine learning model's top 10 most influential features affecting churn:
+
+Feature | Importance:
+-------------------------------
+NumOfProducts | 0.323888
+IsActiveMember | 0.164146
+Age | 0.109550
+Geography_Germany | 0.091373
+Balance | 0.052786
+Geography_France | 0.046463
+Gender_Female | 0.045283
+Geography_Spain | 0.036855
+CreditScore | 0.035005
+EstimatedSalary | 0.032655
+HasCrCard | 0.031940
+Tenure | 0.030054
+Gender_Male | 0.000000
+
+{pd.set_option('display.max_columns', None)}
+
+Here are the summary statistics for churned customers:
+{df[df['Exited'] == 1].describe()}
+
+Here are the summary statistics for non-churned customers:
+{df[df['Exited'] == 0].describe()}
+
+Based on the customer’s probability of churning:
+- If the probability is above 40%, generate a brief 3-sentence explanation outlining why the customer is at risk of churning.
+- If the probability is below 40%, generate a 3-sentence explanation of why the customer may not be at risk of churning.
+
+The output should only be the explanation itself, based on the customer's information, the summary statistics of churned and non-churned customers, and the most influential features, without mentioning probability, model, or feature names. No extra text or summaries are needed.
+"""
+
+    raw_response = client.chat.completions.create(
+        model="llama-3.2-3b-preview",
+        messages=[{"role": "user", "content": prompt}],
+        temperature=0.5
+    )
+    return raw_response.choices[0].message.content
+
+st.title("Customer Churn Predictor")
+
+df = pd.read_csv('churn.csv')
+
+customers = [f"{row['CustomerId']} - {row['Surname']}" for _, row in df.iterrows()]
+
+selected_customer_option = st.selectbox("Select a customer", customers)
+
+if selected_customer_option:
+    selected_customer_id = selected_customer_option.split(' - ')[0]
+    selected_customer_surname = selected_customer_option.split(' - ')[1]
+    selected_customer = df.loc[df["CustomerId"] == int(selected_customer_id)].iloc[0]
+
+    col1, col2 = st.columns(2)
+
+    with col1:
+        credit_score = st.number_input(
+            "Credit Score", 
+            min_value=300,
+            max_value=850,
+            value=selected_customer["CreditScore"]
+        )
+        
+        location = st.selectbox(
+            "Location",
+            ["France", "Spain", "Germany"],
+            index=["France", "Spain", "Germany"].index(selected_customer["Geography"])
+        )
+
+        gender = st.radio(
+            "Gender",
+            ["Male", "Female"],
+            index=0 if selected_customer["Gender"] == "Male" else 1
+        )
+
+        age = st.number_input(
+            "Age",
+            min_value=18,
+            max_value=100,
+            value=int(selected_customer["Age"])
+        )
+
+        tenure = st.number_input(
+            "Tenure (years)",
+            min_value=0,
+            max_value=50,
+            value=int(selected_customer["Tenure"])
+        )
+
+    with col2:
+        balance = st.number_input(
+            "Balance",
+            min_value=0.0,
+            value=float(selected_customer["Balance"])
+        )
+
+        num_products = st.number_input(
+            "Number of Products",
+            min_value=1,
+            max_value=10,
+            value=int(selected_customer["NumOfProducts"])
+        )   
+
+        has_credit_card = st.checkbox(
+            "Has Credit Card",
+            value=bool(selected_customer["HasCrCard"])
+        )
+
+        is_active_member = st.checkbox(
+            "Active Member",
+            value=bool(selected_customer["IsActiveMember"])
+        )
+
+        estimated_salary = st.number_input(
+            "Estimated Salary",
+            min_value=0.0,
+            value=float(selected_customer["EstimatedSalary"])
+        )
+
+    input_df, input_dict = prepare_input_data(credit_score, location, gender, age, tenure, balance, num_products, has_credit_card, is_active_member, estimated_salary)
+    avg_probability = make_prediction(input_df, input_dict)
+    explanation = explain_prediction(avg_probability, input_dict, selected_customer_surname)
+
+    st.markdown("---")
+    st.subheader("Explanation of the Prediction")
+    st.markdown(explanation)

dt_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47290e1986e9925480105482f591ae0827b421002be55543ca3709c6e8e867b9
+size 185395

knn_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5799130c75678bf3370eb3bec2b8f56a3750be8b9242cc70da347278c2015bd
+size 1083831

nb_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0945f3afbd7ad8ef7d93a119329ea5caf08bd727d5d9f9b3afe1b9ecb6c698df
+size 993

requirements.txt

@@ -0,0 +1,8 @@
+streamlit
+pandas
+numpy
+openai
+plotly
+scikit-learn
+imbalanced-learn
+xgboost

rf_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94e077bee37c812d1233991d6a21bd4e989dece9f192c9c20642233323f56d74
+size 18868305

svm_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f3fd771fddc7ee9abe0f07d0f16a240e48fb9b97fe6cd2ebe058d90c91311d1
+size 369521

train_models.py

@@ -0,0 +1,135 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from sklearn.ensemble import VotingClassifier
+from sklearn.metrics import classification_report, accuracy_score, confusion_matrix
+import pickle
+#models
+from sklearn.linear_model import LogisticRegression
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.svm import SVC
+from sklearn.naive_bayes import GaussianNB
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.tree import DecisionTreeClassifier
+import xgboost as xgb
+#Improving accuracy
+from imblearn.over_sampling import SMOTE
+
+df = pd.read_csv('churn.csv')
+
+sns.set_style(style="whitegrid")
+plt.figure(figsize=(12, 10))
+
+#sns.countplot(x='Exited', data=df)
+plt.title('Churn Distribution')
+#sns.histplot(data=df, x='Age', kde=True)
+plt.title('Age Distribution')
+
+#sns.scatterplot(data=df, x='CreditScore', y='Age', hue='Exited')
+plt.title('Credit Score vs Age')
+
+#sns.boxplot(data=df, x='Exited', y='Balance')
+plt.title('Balance vs Churn')
+
+#sns.boxplot(x='Exited', y='CreditScore', data=df)
+plt.title('Credit Score vs Churn')
+#plt.show()
+
+#Feature Engineering
+features = df.drop(columns=['Exited', 'RowNumber', 'CustomerId', 'Surname'])
+features["CLV"] = df["Balance"] * df["EstimatedSalary"] / 100000
+features["AgeGroup"] = pd.cut(df["Age"], bins=[0, 30, 45, 60, 100], labels=["Young", "MiddleAged", "Senior", "Elderly"])
+features["TenureAgeRatio"] = df["Tenure"] / df["Age"]
+features = pd.get_dummies(features, columns=['Geography', 'Gender', 'AgeGroup'])
+target = df['Exited']
+
+#Train Test Split
+X_train, X_test, y_train, y_test = train_test_split(features, target, test_size=0.2, random_state=42)
+
+scaler = StandardScaler()
+X_train = scaler.fit_transform(X_train)
+X_test = scaler.fit_transform(X_test)
+
+#SMOTE
+smote = SMOTE(random_state=42)
+X_resampled, y_resampled = smote.fit_resample(X_train, y_train)
+
+#Logistic Regression
+lr_model = LogisticRegression(random_state=42)
+lr_model.fit(X_train, y_train)
+
+lr_pred = lr_model.predict(X_test)
+
+lr_accuracy = accuracy_score(y_test, lr_pred)
+
+#Model Evaluation and Saving
+def evaluate_model(model, X_train, y_train, X_test, y_test):
+    model.fit(X_train, y_train)
+    y_pred = model.predict(X_test)
+    accuracy = accuracy_score(y_test, y_pred)
+    print(f"{model.__class__.__name__} Accuracy: {accuracy}")
+    print(f"\nClassification Report:\n{classification_report(y_test, y_pred)}")
+    print(f"--------------------------------")
+
+
+def evaluate_and_save_model(model, X_train, y_train, X_test, y_test, file_name):
+    model.fit(X_train, y_train)
+    y_pred = model.predict(X_test)
+    accuracy = accuracy_score(y_test, y_pred)
+    print(f"{model.__class__.__name__} Accuracy: {accuracy}")
+    print(f"\nClassification Report:\n{classification_report(y_test, y_pred)}")
+    print(f"--------------------------------")
+
+    with open(file_name, 'wb') as file:
+        pickle.dump(model, file)
+    
+    print(f"Model saved to {file_name}")
+""" 
+xgb_model = xgb.XGBClassifier(random_state=42)
+#evaluate_and_save_model(xgb_model, X_train, y_train, X_test, y_test, 'xgb_model.pkl')
+evaluate_model(xgb_model, X_train, y_train, X_test, y_test)
+evaluate_and_save_model(xgb_model, X_resampled, y_resampled, X_test, y_test, 'xgb_model_resampled.pkl')
+
+dt_model = DecisionTreeClassifier(random_state=42)
+#evaluate_and_save_model(dt_model, X_train, y_train, X_test, y_test, 'dt_model.pkl')
+evaluate_model(dt_model, X_train, y_train, X_test, y_test)
+
+rf_model = RandomForestClassifier(random_state=42)
+evaluate_and_save_model(rf_model, X_train, y_train, X_test, y_test, 'rf_model.pkl')
+
+nb_model = GaussianNB()
+evaluate_and_save_model(nb_model, X_train, y_train, X_test, y_test, 'nb_model.pkl')
+
+svm_model = SVC(random_state=42)
+evaluate_and_save_model(svm_model, X_train, y_train, X_test, y_test, 'svm_model.pkl')
+
+knn_model = KNeighborsClassifier()
+evaluate_and_save_model(knn_model, X_train, y_train, X_test, y_test, 'knn_model.pkl')
+
+#Feature Importance
+feature_imporance = xgb_model.feature_importances_
+feature_names = features.columns
+
+feature_importance_df = pd.DataFrame({
+    'Feature': feature_names, 'Importance': feature_imporance
+})
+
+feature_importance_df = feature_importance_df.sort_values(by='Importance', ascending=False)
+
+ """
+#Voting Classifier
+""" 
+voting_model = VotingClassifier(
+    estimators=[('xgb', xgb.XGBClassifier(random_state=42)), ('rf', RandomForestClassifier(random_state=42)), ('svm', SVC(random_state=42, probability=True))], 
+    voting='hard'
+)
+evaluate_and_save_model(voting_model, X_train, y_train, X_test, y_test, 'voting_model.pkl') """
+""" 
+plt.figure(figsize=(10, 6))
+plt.barh(feature_importance_df['Feature'], feature_importance_df['Importance'])
+plt.xticks(rotation=90)
+plt.xlabel('Importance')
+plt.ylabel('Feature')
+plt.title('Feature Importance') """

utils.py

@@ -0,0 +1,74 @@
+import plotly.graph_objects as go
+
+def create_guage_chart(probability):
+    if probability > 0.3:
+        color = 'green'
+    elif probability < 0.6:
+        color = 'yellow'
+    else:
+        color = 'red'
+
+    fig = go.Figure(
+        go.Indicator(
+            mode = "gauge+number",
+            value = probability * 100,
+            domain = {'x': [0, 1], 'y': [0, 1]},
+            title = {'text': "Churn Probability", 'font': {'size': 24, 'color': 'white'}},
+            number = {'font': {'size': 40, 'color': 'white'}},
+            gauge = {
+                'axis': {
+                    'tickwidth': 1,
+                    'range': [0, 100],
+                    'tickcolor': 'white',
+                    },
+                'bar': {'color': color},
+                'bgcolor': 'rgba(0,0,0,0)',
+                'borderwidth': 2,
+                'bordercolor': 'white',
+                'steps': [
+                    {'range': [0, 30], 'color': 'rgba(0,255,0,0.3)'},
+                    {'range': [30, 60], 'color': 'rgba(255,255,0,0.3)'},
+                    {'range': [60, 100], 'color': 'rgba(255,0,0,0.3)'}
+                ],
+                'threshold': {
+                    'line': {'color': 'white', 'width': 4},
+                    'thickness': 0.75,
+                    'value': 100
+                }
+            }
+        )
+    )
+    fig.update_layout(
+        paper_bgcolor = 'rgba(0,0,0,0)',
+        plot_bgcolor = 'rgba(0,0,0,0)',
+        font = {'color': 'white'},
+        width = 400,
+        height = 300,
+        margin = dict(l=20, r=20, t=50, b=20)
+    )
+    return fig
+
+def create_model_probability_chart(probabilities):
+    models = list(probabilities.keys())
+    probs = list(probabilities.values())
+
+    fig = go.Figure(
+        data = [
+            go.Bar(
+                y=models,
+                x=probs,
+                orientation='h',
+                text=[f'{p:.2f}%' for p in probs],
+                textposition='auto',
+            )
+        ]
+    )
+    fig.update_layout(
+        title = 'Churn Probabilities by Model',
+        yaxis_title = 'Models',
+        xaxis_title = 'Churn Probability',
+        xaxis = dict(tickformat='.0%', range=[0, 1]),
+        height = 400,
+        margin = dict(l=20, r=20, t=40, b=20)
+    )
+    return fig

voting_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc5c5b182532de2d10b3c4a2d1b93cdacda8ccc60d3ae6b2dbf8138505b531b
+size 19540897

xgb_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:163a465cbc4464bc46375b5ba8e3506baff402c973388800ab22b6d9bb214e87
+size 302532

xgb_resampled_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d93d9602c5aa5e929274855b1afc8a8230c6d820f475cb857391d57ab1bcdc74
+size 299798