Create app.py

app.py

@@ -0,0 +1,140 @@
+# -*- coding: utf-8 -*-
+"""Untitled32.ipynb
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/1fKN0jOoDSOaUCMAAoxNUnSUd-HPcRXNZ
+"""
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.ensemble import RandomForestClassifier
+from lightgbm import LGBMClassifier
+from sklearn.model_selection import train_test_split
+
+import streamlit as st
+import pandas as pd
+import matplotlib.pyplot as plt
+import numpy as np
+
+data = pd.read_csv('archive (8).zip')
+data.head()
+
+to_use_cols = ['as_of_year', 'county_name', 'applicant_sex_name', 'action_taken_name', 'loan_amount_000s', 'applicant_income_000s', 'state_name', 'property_type_name', 'loan_type_name']
+
+data_reduced = data[to_use_cols]
+data_reduced.head()
+
+data_reduced.shape
+
+data_no_na = data_reduced.dropna()
+
+data_no_na.shape
+
+data_no_na.action_taken_name.value_counts()
+
+succeeded = ['Loan originated', 'Loan purchased by the institution', ]
+failed = ['Application approved but not accepted', 'Preapproval request denied by financial institution', 'Application denied by financial institution', 'Preapproval request approved but not accepted']
+user_error = ['File closed for incompleteness', 'Application withdrawn by applicant', ]
+
+mapped = {tuple(succeeded): 1, tuple(failed): 2, tuple(user_error): 3}
+
+def mapped(x):
+  if x in succeeded:
+    return 1
+  elif x in failed:
+    return 0
+  else:
+    return 2
+
+data_no_na.action_taken_name = data_no_na.action_taken_name.apply(mapped)
+
+data_no_na.loan_type_name.value_counts()
+
+mapped_type = {
+    'Conventional': 0,
+    'FHA-insured': 1,
+    'VA-guaranteed':2,
+    'FSA/RHS-guaranteed':3
+}
+
+data_no_na.loan_type_name.apply(lambda x: mapped_type[x])
+
+data_no_na['loan_encoded'] = data_no_na.loan_type_name.apply(lambda x: mapped_type[x])
+
+data_no_na.property_type_name.value_counts()
+
+data_no_na['property_encoded'] = data_no_na.property_type_name.apply(lambda x: 1 if x == 'Manufactured housing' else 0)
+
+data_no_na.state_name.value_counts()
+
+data_no_na.county_name.value_counts()
+
+data_no_na.county_name.unique()
+
+code = {}
+i = 0
+for county in data_no_na.county_name.unique():
+  code[county] = i
+  i += 1
+
+data_no_na['county_code']= data_no_na.county_name.map(code)
+
+data_no_na.head(2)
+
+data_no_na['sex_encoded'] = data_no_na.applicant_sex_name.apply(lambda x: 1 if x == 'Male' else 0)
+
+data_no_na.head(2)
+
+cols = ['county_code', 'sex_encoded', 'property_encoded', 'loan_encoded', 'applicant_income_000s', 'loan_amount_000s', 'action_taken_name']
+
+train = data_no_na[cols]
+
+X_train, X_test, y_train,  y_test = train_test_split(train, train.action_taken_name, test_size=0.3, random_state=42)
+
+
+gbm = LGBMClassifier(n_estimators=200)
+random = RandomForestClassifier(n_estimators=200)
+tree = DecisionTreeClassifier()
+
+gbm.fit(X_train, y_train)
+random.fit(X_train, y_train)
+tree.fit(X_train, y_train)
+
+def mapping(**kwargs):
+  kwargs['sex'] = 1 if kwargs['sex'] == 'Male' else 0
+  kwargs['property_type'] =  1 if kwargs['property_type'] == 'Manufactured housing' else 0
+  kwargs['loan'] = float(kwargs['loan'])
+  kwargs['income'] = float(kwargs['income'])
+  kwargs['loan_amount'] = float(kwargs['loan_amount'])
+  kwargs['county'] = code[kwargs['county']]
+  return kwargs
+
+
+st.title('Loan Approval for Washington House')
+
+col1, col2 = st.columns([3, 1])
+with col1:
+  st.text('Please, fill this form')
+
+  with st.form("my_form"):
+    county = st.selectbox('County', data_no_na.county_name.unique().tolist())
+    sex = st.selectbox('Sex', ['Male', 'Female'])
+    property_type = st.selectbox('Property Type', data_no_na.property_type_name.unique().tolist())
+    loan = st.selectbox('Loan Type', data_no_na.loan_type_name.unique().tolist())
+    income = st.number_input('Your Yearly income (in 000$)')
+    loan_amount = st.number_input('Loan Amount')
+
+    model_choice = col2.selectbox('Choose model', ['RandomForest', 'Tree', 'LGBM'])
+    # Every form must have a submit button.
+    submitted = st.form_submit_button("Submit")
+    if submitted:
+        st.info('Predicting')
+        new_demand = np.array(mapping(county=county, sex=sex, property_type=property_type, loan=loan, income=income, loan_amount=loan_amount))
+        if model_choice == 'Tree':
+          st.text(tree.predict(new_demand))
+        elif model_choice == 'RandomForest':
+          st.text(random.predict(new_demand))
+        else:
+          st.text(gbm.predict(new_demand))
+
+