MLModel.py

# -*- coding: utf-8 -*-
"""model.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1Eil6PhEPgl1OUaTOWOe8-VQpYzbnJe-_
"""

import numpy as np
import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.tree import plot_tree
from sklearn.metrics import accuracy_score
from pandas.plotting import parallel_coordinates
import matplotlib.pyplot as plt
import plotly.express as px

#we need to create some sample data in a csv format with parameters like age, race, gender, health history and then their respective policy tier
df = pd.read_csv("insurance_data.csv")
print(df)
X = df[['age', 'gender', 'race', 'income', 'smoker', 'alcohol', 'exercise', 'risk']]
y = df['policy_tier']

#splitting the data into training and test data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

#training the model
clf = DecisionTreeClassifier()
clf.fit(X_train, y_train)

print(X_test)

y_pred = clf.predict(X_test)
print(y_pred)

y_pred = clf.predict(X_test)

accuracy = accuracy_score(y_test, y_pred)
print("Accuracy of the prediction is:")
print(accuracy * 100)

plt.figure(figsize=(20,10))
plot_tree(clf, feature_names=['age', 'gender', 'race', 'income', 'smoker', 'alcohol', 'exercise', 'risk'], class_names=['1', '2', '3', '4', '5', '6', '7', '8'], filled=True);
plt.show()

#@title Enter Parameters { display-mode: "code" }

#Age
Age = 35 #@param {type:"integer"}

#Gender
Gender = "Female" #@param ["Male", "Female"]
if Gender == "Male":
  GENDER = 1
else:
  GENDER = 0

#Race
Race = "Malay" #@param ["Chinese", "Malay", "Indian"]
if Race == "Chinese":
  RACE = 2.0
elif Race == "Malay":
  RACE = 3.0
else:
  RACE = 1.0

#Income
Income = 5000 #@param {type:"integer"}

#Smoker
Smoker = False #@param {type:"boolean"}
if Smoker == False:
  SMOKER = 0
else:
  SMOKER = 1

#Alcohol
Alcohol = "Light" #@param ["Never", "Light", "Moderate", "Heavy"]
if Alcohol == "Never":
  ALCOHOL = 0
elif Alcohol == "Light":
  ALCOHOL = 1
elif Alcohol == "Moderate":
  ALCOHOL = 2
else:
  ALCOHOL = 3

#Exercise
Exercise = "Moderate" #@param ["Never", "Light", "Moderate", "Heavy"]
if Exercise == "Never":
  EXERCISE = 0
elif Exercise == "Light":
  EXERCISE = 1
elif Exercise == "Moderate":
  EXERCISE = 2
else:
  EXERCISE = 3

#Risk
Risk = "1" #@param ["1", "2", "3", "4", "5"]

new_customer = [[Age, GENDER, RACE, Income, SMOKER, ALCOHOL, EXERCISE, Risk]]


print(new_customer[0])
new_customer_policy_tier = clf.predict(new_customer)
print("Recommended policy tier for new customer:", new_customer_policy_tier[0])

print(new_customer[0][0])
AGE_NC = new_customer[0][0]

#groups the customers by age group
age_groups = df.groupby("age")

#calculates the proportion of customers in each age group that choose each policy tier
age_stats = age_groups["policy_tier"].value_counts(normalize=True)

#prints the statistics for the new customer's age group
print(age_stats)

print(new_customer[0][0])

#groups the customers by age group
age_groups = df.groupby("age")

#calculates the proportion of customers in each age group that choose each policy tier
age_stats = age_groups["policy_tier"].value_counts(normalize=True)

#prints the statistics for the new customer's age group
age = new_customer[0][0]
print(age_stats[age])

#counts the number of customers in each age group
age_counts = df['age'].value_counts()

#prints the counts for the new customer's age group
age = new_customer[0][0]
print(age_counts[age])

df.groupby('age').size()

#creating a scatter plot of income vs policy_tier
plt.scatter(df['income'], df['policy_tier'])
plt.xlabel('Income')
plt.ylabel('Policy Tier')
plt.title('Income vs Policy Tier')

#overlaying a single point for new customer data
plt.scatter(new_customer[0][3], clf.predict(new_customer), c='red', marker='*', s=200)

plt.show()