Add Flask API files

flask_api/server.py

@@ -0,0 +1,68 @@
+import os
+import pandas as pd
+import dill as pickle
+from flask import Flask, jsonify, request
+from utils import PreProcessing
+
+app = Flask(__name__)
+
+@app.route('/predict', methods=['POST'])
+def apicall():
+	"""API Call
+	
+	Pandas dataframe (sent as a payload) from API Call
+	"""
+	try:
+		test_json = request.get_json()
+		test = pd.read_json(test_json, orient='records')
+
+		#To resolve the issue of TypeError: Cannot compare types 'ndarray(dtype=int64)' and 'str'
+		test['Dependents'] = [str(x) for x in list(test['Dependents'])]
+
+		#Getting the Loan_IDs separated out
+		loan_ids = test['Loan_ID']
+
+	except Exception as e:
+		raise e
+	
+	clf = 'model_v1.pk'
+	
+	if test.empty:
+		return(bad_request())
+	else:
+		#Load the saved model
+		print("Loading the model...")
+		loaded_model = None
+		with open('./models/'+clf,'rb') as f:
+			loaded_model = pickle.load(f)
+
+		print("The model has been loaded...doing predictions now...")
+		predictions = loaded_model.predict(test)
+		
+		"""Add the predictions as Series to a new pandas dataframe
+								OR
+		   Depending on the use-case, the entire test data appended with the new files
+		"""
+		prediction_series = list(pd.Series(predictions))
+
+		final_predictions = pd.DataFrame(list(zip(loan_ids, prediction_series)))
+		
+		"""We can be as creative in sending the responses.
+		   But we need to send the response codes as well.
+		"""
+		responses = jsonify(predictions=final_predictions.to_json(orient="records"))
+		responses.status_code = 200
+
+		return (responses)
+
+
+@app.errorhandler(400)
+def bad_request(error=None):
+	message = {
+			'status': 400,
+			'message': 'Bad Request: ' + request.url + '--> Please check your data payload...',
+	}
+	resp = jsonify(message)
+	resp.status_code = 400
+
+	return resp

flask_api/utils.py

@@ -0,0 +1,96 @@
+import os 
+import json
+import numpy as np
+import pandas as pd
+import dill as pickle
+from sklearn.externals import joblib
+from sklearn.model_selection import train_test_split, GridSearchCV
+from sklearn.base import BaseEstimator, TransformerMixin
+from sklearn.ensemble import RandomForestClassifier
+
+from sklearn.pipeline import make_pipeline
+
+import warnings
+warnings.filterwarnings("ignore")
+
+
+def build_and_train():
+
+	data = pd.read_csv('../data/training.csv')
+	data = data.dropna(subset=['Gender', 'Married', 'Credit_History', 'LoanAmount'])
+
+	pred_var = ['Gender','Married','Dependents','Education','Self_Employed','ApplicantIncome','CoapplicantIncome',\
+				'LoanAmount','Loan_Amount_Term','Credit_History','Property_Area']
+
+	X_train, X_test, y_train, y_test = train_test_split(data[pred_var], data['Loan_Status'], \
+														test_size=0.25, random_state=42)
+	y_train = y_train.replace({'Y':1, 'N':0}).as_matrix()
+	y_test = y_test.replace({'Y':1, 'N':0}).as_matrix()
+
+	pipe = make_pipeline(PreProcessing(),
+						RandomForestClassifier())
+
+	param_grid = {"randomforestclassifier__n_estimators" : [10, 20, 30],
+				 "randomforestclassifier__max_depth" : [None, 6, 8, 10],
+				 "randomforestclassifier__max_leaf_nodes": [None, 5, 10, 20], 
+				 "randomforestclassifier__min_impurity_split": [0.1, 0.2, 0.3]}
+
+	grid = GridSearchCV(pipe, param_grid=param_grid, cv=3)
+
+	grid.fit(X_train, y_train)
+
+	return(grid)
+
+
+class PreProcessing(BaseEstimator, TransformerMixin):
+    """Custom Pre-Processing estimator for our use-case
+    """
+
+    def __init__(self):
+        pass
+
+    def transform(self, df):
+        """Regular transform() that is a help for training, validation & testing datasets
+           (NOTE: The operations performed here are the ones that we did prior to this cell)
+        """
+        pred_var = ['Gender','Married','Dependents','Education','Self_Employed','ApplicantIncome',\
+                    'CoapplicantIncome','LoanAmount','Loan_Amount_Term','Credit_History','Property_Area']
+        
+        df = df[pred_var]
+        
+        df['Dependents'] = df['Dependents'].fillna(0)
+        df['Self_Employed'] = df['Self_Employed'].fillna('No')
+        df['Loan_Amount_Term'] = df['Loan_Amount_Term'].fillna(self.term_mean_)
+        df['Credit_History'] = df['Credit_History'].fillna(1)
+        df['Married'] = df['Married'].fillna('No')
+        df['Gender'] = df['Gender'].fillna('Male')
+        df['LoanAmount'] = df['LoanAmount'].fillna(self.amt_mean_)
+        
+        gender_values = {'Female' : 0, 'Male' : 1} 
+        married_values = {'No' : 0, 'Yes' : 1}
+        education_values = {'Graduate' : 0, 'Not Graduate' : 1}
+        employed_values = {'No' : 0, 'Yes' : 1}
+        property_values = {'Rural' : 0, 'Urban' : 1, 'Semiurban' : 2}
+        dependent_values = {'3+': 3, '0': 0, '2': 2, '1': 1}
+        df.replace({'Gender': gender_values, 'Married': married_values, 'Education': education_values, \
+                    'Self_Employed': employed_values, 'Property_Area': property_values, \
+                    'Dependents': dependent_values}, inplace=True)
+        
+        return df.as_matrix()
+
+    def fit(self, df, y=None, **fit_params):
+        """Fitting the Training dataset & calculating the required values from train
+           e.g: We will need the mean of X_train['Loan_Amount_Term'] that will be used in
+                transformation of X_test
+        """
+        
+        self.term_mean_ = df['Loan_Amount_Term'].mean()
+        self.amt_mean_ = df['LoanAmount'].mean()
+        return self
+
+if __name__ == '__main__':
+	model = build_and_train()
+
+	filename = 'model_v1.pk'
+	with open('../flask_api/models/'+filename, 'wb') as file:
+		pickle.dump(model, file)