feat: health insurance app

.gitignore

@@ -0,0 +1 @@
+flagged/log.csv

app.py

@@ -1,7 +1,56 @@
+import joblib
 import gradio as gr
+from models import HealthInsurance
 
-def greet(name):
-    return "Hello " + name + "!!"
+def load_data():
+    global _model 
+    global _column_transformer
+    global _bins_annual_premium_type
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+    _model = joblib.load(filename = 'parameters/random_forrest.gz')
+    _column_transformer = joblib.load(filename = 'parameters/column_transformer.joblib')
+    _bins_annual_premium_type = joblib.load(filename = 'parameters/bins_annual_premium_type.joblib')
+
+def predict(df):
+
+    health_insurance = HealthInsurance(_model,_column_transformer,
+                                            _bins_annual_premium_type)
+    
+    df_predicted = health_insurance.predict(df)   
+
+    return df_predicted
+
+def input():
+    return gr.Dataframe(headers = ['previously_insured',
+                                    'annual_premium','vintage','gender',
+                                    'age','region_code','policy_sales_channel',
+                                    'driving_license','vehicle_age',
+                                    'vehicle_damage'],
+                        datatype = ['number','number','number','str','number',
+                                    'number','number','number','str','str'],
+                        row_count= 1,
+                        col_count= (10,'fixed'),
+                        type = 'pandas',
+                        label = 'Input')
+
+def output():
+    return gr.Dataframe(headers = ['previously_insured',
+                                    'annual_premium','vintage','gender',
+                                    'age','region_code','policy_sales_channel',
+                                    'driving_license','vehicle_age',
+                                    'vehicle_damage', 'score'],
+                        datatype = ['number','number','number','str','number',
+                                    'number','number','number','str','str',
+                                    'number'],
+                        type = 'pandas',
+                        label = 'Output')
+
+if __name__ == "__main__":
+
+    load_data()
+    iface = gr.Interface(fn=predict, 
+                        inputs=input(), 
+                        outputs=output(),
+                        title='Health Insurance App'
+                        )
+    iface.launch()

models/HealthInsurance.py

@@ -15,9 +15,13 @@ class HealthInsurance():
 
 
     def feature_engineering(self, df):
-        premium_categories = ['very_low', 'low', 'moderate', 'high', 'very_high']
+
+        df[['previously_insured','vintage','age','driving_license']] = df[['previously_insured','vintage','age','driving_license']].astype(int)
+        df[['annual_premium','region_code','policy_sales_channel']] = df[['annual_premium','region_code','policy_sales_channel']].astype(float)
 
         df['vehicle_age'] = df['vehicle_age'].apply(self.get_vehicle_age)
+
+        premium_categories = ['very_low', 'low', 'moderate', 'high', 'very_high']
         df['annual_premium_type'] = pd.cut(x = df['annual_premium'], 
                                             bins = self.bins_annual_premium_type,
                                             labels = premium_categories)
@@ -36,16 +40,15 @@ class HealthInsurance():
     def data_preparation(self, df):        
         return self.transformer.transform(df)
     
-    def predict(self, payload):
-        df = pd.read_json(payload, orient='records')
-
+    def predict(self, df):
+        
         np_array = (df.pipe(self.feature_engineering)
                          .pipe(self.data_preparation)
                     )
 
-        df['score'] = self.model.predict_proba(np_array)[:, 1]
-
-        return df.to_json(orient='records')
+        df['score'] = self.model.predict_proba(np_array)[:, 1]  
+        df.drop('annual_premium_type', axis=1, inplace=True) 
+        return df
 
 
 

requirements.txt

@@ -1,23 +1,68 @@
+aiohttp==3.8.1
+aiosignal==1.2.0
+analytics-python==1.4.0
+anyio==3.6.1
+async-timeout==4.0.2
+attrs==22.1.0
+backoff==1.10.0
+bcrypt==4.0.0
 category-encoders==2.5.0
+certifi==2022.6.15
+cffi==1.15.1
+charset-normalizer==2.1.1
 click==8.1.3
-deprecation==2.1.0
-Flask==2.2.2
-itsdangerous==2.1.2
+cryptography==38.0.1
+cycler==0.11.0
+fastapi==0.82.0
+ffmpy==0.3.0
+fonttools==4.37.1
+frozenlist==1.3.1
+fsspec==2022.8.2
+gradio==3.2
+h11==0.12.0
+httpcore==0.15.0
+httpx==0.23.0
+idna==3.3
 Jinja2==3.1.2
 joblib==1.1.0
+kiwisolver==1.4.4
+linkify-it-py==1.0.3
+markdown-it-py==2.1.0
 MarkupSafe==2.1.1
+matplotlib==3.5.3
+mdit-py-plugins==0.3.0
+mdurl==0.1.2
+monotonic==1.6
+multidict==6.0.2
 numpy==1.23.2
+orjson==3.8.0
 packaging==21.3
 pandas==1.4.4
+paramiko==2.11.0
 patsy==0.5.2
+Pillow==9.2.0
+pycparser==2.21
+pycryptodome==3.15.0
+pydantic==1.10.2
+pydub==0.25.1
+PyNaCl==1.5.0
 pyparsing==3.0.9
 python-dateutil==2.8.2
+python-multipart==0.0.5
 pytz==2022.2.1
+requests==2.28.1
+rfc3986==1.5.0
 scikit-learn==1.1.2
 scipy==1.9.1
 six==1.16.0
 sklearn==0.0
+sniffio==1.3.0
+starlette==0.19.1
 statsmodels==0.13.2
 threadpoolctl==3.1.0
-watchdog==2.1.9
-Werkzeug==2.2.2
+typing_extensions==4.3.0
+uc-micro-py==1.0.1
+urllib3==1.26.12
+uvicorn==0.18.3
+websockets==10.3
+yarl==1.8.1