Ml model

Pipfile

@@ -0,0 +1,11 @@
+[[source]]
+name = "pypi"
+url = "https://pypi.org/simple"
+verify_ssl = true
+
+[dev-packages]
+
+[packages]
+
+[requires]
+python_version = "3.6"

model.py

@@ -1,17 +1,19 @@
+'''
+
+
+
+
+
+
+
+'''
 import pandas as pd
 import numpy as np
-%matplotlib inline
-import matplotlib.pyplot as plt
-import matplotlib.lines as mlines
-from mpl_toolkits.mplot3d import Axes3D
-import seaborn as sns
 from sklearn.model_selection import train_test_split, learning_curve
 from sklearn.metrics import average_precision_score
-from xgboost.sklearn import XGBClassifier
-from xgboost import plot_importance, to_graphviz
+from sklearn.linear_model import LogisticRegression
 import pickle
 
-
 df = pd.read_csv('Fraud_data_kaggle.csv')
 X = df.loc[(df.type == 'TRANSFER') | (df.type == 'CASH_OUT')]
 
@@ -57,11 +59,9 @@
                                                 random_state = randomState)
 
 # Long computation in this cell (~1.8 minutes)
-weights = (Y == 0).sum() / (1.0 * (Y == 1).sum())
-clf = XGBClassifier(max_depth = 3, scale_pos_weight = weights, \
-                n_jobs = 4)
-probabilities = clf.fit(trainX, trainY).predict_proba(testX)
-print('AUPRC = {}'.format(average_precision_score(testY, \
-                                              probabilities[:, 1])))
-
-pickle.dump(clf, open('final_prediction.pkl', 'wb'))      
+# weights = (Y == 0).sum() / (1.0 * (Y == 1).sum())
+clf = LogisticRegression()
+log = clf.fit(trainX, trainY)
+predict = log.predict(testX)  
+
+pickle.dump(log, open('logistic.pkl', 'wb'))

predict.py

@@ -0,0 +1,55 @@
+import numpy as np
+import sys
+import pickle
+
+model = pickle.load(open('final_prediction.pickle', 'rb'))
+
+
+def predict(argv):
+
+    int_features = [int(x) for x in argv[1:]]
+    final_features = [np.array(int_features)]
+    prediction = model.predict(final_features)
+
+    output = prediction[0]
+
+    return output
+
+
+if __name__ == '__main__':
+    predict(sys.argv)
+
+
+# app = Flask(__name__)
+# from flask import Flask, request, jsonify, render_template
+
+
+# @app.route('/')
+# def home():
+#     return render_template('index.html')
+
+
+# @app.route('/predict', methods=['POST'])
+# def predict():
+
+#     int_features = [int(x) for x in request.form.values()]
+#     final_features = [np.array(int_features)]
+#     prediction = model.predict(final_features)
+
+#     output = round(prediction[0], 2)
+
+#     return render_template('index.html', prediction_text='This transaction is likely to be fraud in percentage by $ {}'.format(output))
+
+
+# @app.route('/results', methods=['POST'])
+# def results():
+
+#     data = request.get_json(force=True)
+#     prediction = model.predict([np.array(list(data.values()))])
+
+#     output = prediction[0]
+#     return jsonify(output)
+
+
+# if __name__ == "__main__":
+#     app.run(debug=True)

request.py

@@ -0,0 +1,10 @@
+import requests
+
+url = 'http://localhost:5000/results'
+r = requests.post(url,json={'step':205, 'type':1, 'oldbalanceOrg':0, 'newbalanceOrig': 0, 'oldbalanceDest': 1853683.32,
+                           'newbalanceDest': 1916926.76, 'errorBalanceOrig': 63243.44, 'errorBalanceDest':0})
+
+print(r.json())
+'''
+
+'''

requirements.txt

@@ -0,0 +1,18 @@
+astroid==2.3.3
+Click==7.0
+colorama==0.4.3
+Flask==1.1.1
+isort==4.3.21
+itsdangerous==1.1.0
+Jinja2==2.11.1
+lazy-object-proxy==1.4.3
+MarkupSafe==1.1.1
+mccabe==0.6.1
+numpy==1.18.1
+pandas==1.0.1
+pylint==2.4.4
+python-dateutil==2.8.1
+pytz==2019.3
+six==1.14.0
+Werkzeug==1.0.0
+wrapt==1.11.2