Update app.py

app.py

@@ -1,67 +1,70 @@
-# This is a small and fast sklearn model, so the run-gradio script trains a model and deploys it
-
-import pandas as pd
 import numpy as np
-import sklearn
-import gradio as gr
-from sklearn import preprocessing
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+url = 'https://raw.githubusercontent.com/MiguelJ125/creditcard_Jaramillo/main/Vehicle_policies_2020.csv' 
+
+df = pd.read_csv(url)
+
+df = df.drop(["pol_number"], axis = 1)
+df = df.drop(["claim_office"], axis = 1)
+df = df.drop(["credit_score"], axis = 1)
+df = df.drop(["annual_premium"], axis = 1)
+df = df.drop(["agecat"], axis = 1)
+
+df=df.dropna()
+
+cleanup_nums = {"area":     {"A": 1, "B": 2, "C": 3, "D": 4, "F": 5, "E": 6}}
+df = df.replace(cleanup_nums) 
+
+from datetime import datetime
+
+datetime = pd.to_datetime(df["date_of_birth"])
+df["date_of_birth"] = datetime
+df = df.copy()
+
+df['date_of_birth'].dt.year
+ahora = pd.Timestamp('now')
+df['Edad'] = (ahora - df['date_of_birth']).astype('<m8[Y]')
+df = df.drop(["date_of_birth"], axis = 1)
+
+df = df.drop(["pol_eff_dt"], axis = 1)
+
+df = pd.get_dummies(df, columns = ["gender"], drop_first = True)
+
+cleanup_nums = {"veh_body":     {"SEDAN": 1, "HBACK": 2, "STNWG": 3, "UTE": 4, "TRUCK": 5, "HDTOP": 6, "COUPE": 7, "PANVN": 8, "MIBUS": 9, "MCARA": 10, "CONVT": 11, "BUS": 12, "RDSTR": 13}}
+df = df.replace(cleanup_nums)
+
+df=df.drop(columns = ['claimcst0'])
+X = df.drop(columns = ['numclaims'])
+y = df['numclaims']
+
+from sklearn.preprocessing import StandardScaler
+scaler = StandardScaler()
+X = scaler.fit_transform(X)
+
 from sklearn.model_selection import train_test_split
-from sklearn.ensemble import RandomForestClassifier
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.10, random_state=1)
+
+from sklearn.tree import DecisionTreeClassifier
 from sklearn.metrics import accuracy_score
 
-data = pd.read_csv('https://raw.githubusercontent.com/gradio-app/titanic/master/train.csv')
-data.head()
-
-def encode_ages(df): # Binning ages 
-    df.Age = df.Age.fillna(-0.5)
-    bins = (-1, 0, 5, 12, 18, 25, 35, 60, 120)
-    categories = pd.cut(df.Age, bins, labels=False)
-    df.Age = categories
-    return df
-
-def encode_fares(df): # Binning fares
-    df.Fare = df.Fare.fillna(-0.5)
-    bins = (-1, 0, 8, 15, 31, 1000)
-    categories = pd.cut(df.Fare, bins, labels=False)
-    df.Fare = categories
-    return df
-
-def encode_sex(df):
-    mapping = {"male": 0, "female": 1}
-    return df.replace({'Sex': mapping})
-
-def transform_features(df):
-    df = encode_ages(df)
-    df = encode_fares(df)
-    df = encode_sex(df)
-    return df
-
-train = data[['PassengerId', 'Fare', 'Age', 'Sex', 'Survived']]
-train = transform_features(train)
-train.head()
-
-
-X_all = train.drop(['Survived', 'PassengerId'], axis=1)
-y_all = train['Survived']
-
-num_test = 0.20
-X_train, X_test, y_train, y_test = train_test_split(X_all, y_all, test_size=num_test, random_state=23)
-
-clf = RandomForestClassifier()
-clf.fit(X_train, y_train)
-predictions = clf.predict(X_test)
-
-def predict_survival(sex, age, fare):
-    df = pd.DataFrame.from_dict({'Sex': [sex], 'Age': [age], 'Fare': [fare]})
-    df = encode_sex(df)
-    df = encode_fares(df)
-    df = encode_ages(df)
-    pred = clf.predict_proba(df)[0]
-    return {'Muere': float(pred[0]), 'Sobrevive': float(pred[1])}
-    
-sex = gr.inputs.Radio(['female', 'male'], label="Sex")
-age = gr.inputs.Slider(minimum=0, maximum=100, default=18, label="age")
-fare = gr.inputs.Slider(minimum=15, maximum=200, default=100, label="Tarifa en libras britanicas")
+tree = DecisionTreeClassifier(max_depth = None)
+tree.fit(X_train, y_train)
 
-gr.Interface(predict_survival, [sex, age, fare], "label", live=True, thumbnail="https://raw.githubusercontent.com/gradio-app/hub-titanic/master/thumbnail.png", analytics_enabled=False,
-    title="Probabilidad de supervivencia", description="").launch();
+def predict_siniestros(area, traf, vage, tipov, valorv, edad, Gen):
+    df = pd.DataFrame.from_dict({'area': [area], 'traffic_indexe': [traf], 'veh_age': [vage], 'veh_body': [tipov], 'veh_value': [valorv], 'Edad': [edad], 'gender_M': [Gen]})
+    
+    pred=tree.predict(df)
+    return {'Es posible que tengas que reclamar al seguro': float(pred[0])}
+    
+area = gr.inputs.Radio(['1', '2', '3', '4', '5', '6'], label="Area: del 1 al 6")
+traf = gr.inputs.Slider(minimum=0, maximum=200, default=100, label="Indice de trafico")
+vage = gr.inputs.Slider(minimum=0, maximum=30, default=1, label="Cantidad de años del vehiculo")
+tipov = gr.inputs.Radio(['1', '2', '3', '4', '5'], label="Tipo de auto (Sedan=1 Hback=2 Family=3 Utilitario=4 Camioneta=5")
+valorv = gr.inputs.Slider(minimum=0, maximum=10, default=1, label="Valor del vehiculo (u$/10.000)")
+edad = gr.inputs.Slider(minimum=16, maximum=100, default=18, label="Edad")
+Gen = gr.inputs.Radio(['1', '0'], label="Genero (F=0 M=1)")
+gr.Interface(predict_siniestros, [area, traf, vage, tipov, valorv, edad, Gen], "label", live=True, thumbnail="https://raw.githubusercontent.com/gradio-app/hub-titanic/master/thumbnail.png", analytics_enabled=False,
+    title="Cuantas veces es probable que tengas que reclamar al seguro en el transcurso de un año", description="Predice la cantidad de veces que por algun siniestro deberas acudir al seguro, con el fin de elegir un plan mas adecuado a cada persona").launch();