GTHACKERS/F-DETECTORS

F-DetectoR/README.md

@@ -0,0 +1,16 @@
+# F-DETECTOR
+
+ML integrated web app to predict the genuinity of transactions by inputting the case details 
+
+# LIBRARIES USED
+- Scikit-learn
+- Pandas
+- Numpy
+- pylab
+- matplotlib
+
+# FRAMEWORKS USED
+- FLASK
+
+# HOW TO CONTRIBUTE?
+Feel free to suggest your opinions by creating an issue or mail us at gthackers4evri1@gmail.com 

F-DetectoR/forms.py

@@ -0,0 +1,16 @@
+from flask_wtf import FlaskForm
+from wtforms import StringField, SubmitField
+from wtforms.validators import DataRequired
+
+
+class CheckForm(FlaskForm):
+    Step = StringField('Step:  ',validators=[DataRequired()])
+    Type = StringField('Type of transaction:  ',validators=[DataRequired()])
+    Amount = StringField('Amount of transaction:  ',validators=[DataRequired()])
+    D_name = StringField('Name of Despositor:  ',validators=[DataRequired()])
+    A_bal_before = StringField('Account balance of depositor before transaction:  ',validators=[DataRequired()])
+    A_bal_after = StringField('Account balance of depositor after transaction:  ',validators=[DataRequired()])
+    P_name = StringField('Name of Payee:  ',validators=[DataRequired()])
+    P_bal_before = StringField('Account balance of Payee before transaction:  ',validators=[DataRequired()])
+    P_bal_after = StringField('Account  balance of Payee after transaction:  ',validators=[DataRequired()])
+    Submit=SubmitField('Submit')

F-DetectoR/model.py

@@ -0,0 +1,82 @@
+# from google.colab import drive
+# drive.mount('/content/gdrive')
+
+import pandas as pd
+
+import numpy as np
+import scipy.optimize as opt
+from sklearn import preprocessing
+# %matplotlib inline 
+import matplotlib.pyplot as plt
+import pylab as pl
+
+
+import pickle #Modifications for flask
+
+text = open("./paysim.csv", "r")
+
+#join() method combines all contents of
+# csvfile.csv and formed as a string
+text = ''.join([i for i in text])
+
+# search and replace the contents
+text = text.replace("PAYMENT", "1")
+text = text.replace("TRANSFER", "2")
+text = text.replace("CASH_IN", "3")
+text = text.replace("CASH_OUT", "4")
+text = text.replace("DEBIT", "5")
+# output.csv is the output file opened in write mode
+x = open("./output.csv", "w")
+
+# all the replaced text is written in the output.csv file
+x.writelines(text)
+x.close()
+
+churn_df = pd.read_csv('./output.csv')
+
+X = np.asarray(churn_df[['step', 'type', 'amount', 'oldbalanceOrg', 'newbalanceOrig',
+        'oldbalanceDest', 'newbalanceDest']])
+
+y = np.asarray(churn_df['isFraud'])
+
+from sklearn import preprocessing
+X = preprocessing.StandardScaler().fit(X).transform(X)
+
+from sklearn.model_selection import train_test_split
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=4)
+
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import confusion_matrix
+LR = LogisticRegression(C=0.01, solver='liblinear').fit(X_train, y_train)
+
+yhat = LR.predict(X_test)
+
+yhat_prob = LR.predict_proba(X_test)
+
+# from sklearn.metrics import jaccard_similarity_score
+# jaccard_similarity_score(y_test, yhat)  #it is an output
+
+# step=float(input())
+# transtype=float(input())
+# amount=float(input())
+# nameorig=str(input())
+# oldbalanceOrg=float(input())
+# newbalanceOrig=float(input())
+# namedest=str(input())
+# oldbalanceDest=float(input())
+# newbalanceDest=float(input())
+
+# Z = [[step, transtype, amount, oldbalanceOrg, newbalanceOrig, oldbalanceDest, newbalanceDest]]
+
+
+from sklearn.linear_model import LogisticRegression
+from sklearn.metrics import confusion_matrix
+LR = LogisticRegression(C=0.01, solver='liblinear').fit(X_train, y_train)
+
+pickle.dump(LR, open('model.pkl', 'wb'))            #Flask modifications
+
+model = pickle.load(open('model.pkl', 'rb'))
+
+
+yhat = LR.predict(Z)
+

F-DetectoR/requirements.txt

@@ -0,0 +1,27 @@
+beautifulsoup4==4.9.3
+click==7.1.2
+cycler==0.10.0
+Flask==1.1.2
+Flask-WTF==0.14.3
+google==3.0.0
+itsdangerous==1.1.0
+Jinja2==2.11.2
+joblib==1.0.0
+kiwisolver==1.3.1
+MarkupSafe==1.1.1
+matplotlib==3.3.3
+numpy==1.19.4
+pandas==1.1.5
+Pillow==8.0.1
+pyparsing==2.4.7
+python-dateutil==2.8.1
+pytz==2020.4
+scikit-learn==0.23.2
+scipy==1.5.4
+six==1.15.0
+sklearn==0.0
+soupsieve==2.1
+SQLAlchemy==1.3.22
+threadpoolctl==2.1.0
+Werkzeug==1.0.1
+WTForms==2.3.3

F-DetectoR/run.py

@@ -0,0 +1,58 @@
+from flask import Flask, render_template, url_for, redirect, request
+import numpy as np
+import pickle
+from forms import CheckForm
+
+
+app = Flask(__name__)
+app.config['SECRET_KEY']='GTHACKERS'
+
+model = pickle.load(open('model.pkl', 'rb'))
+
+@app.route('/')
+def home():
+    return render_template('GT home.html')
+
+
+@app.route('/about')
+def about():
+    return render_template('about.html')
+
+
+@app.route('/contact')
+def contact():
+    return render_template('contact.html')
+
+@app.route('/predict',methods=['GET','POST'])
+def predict():
+    # int_features = [1, 3, 565235956.44242, 13959898.5346, 5464.5434, 21545.54534354, 564.4323434]
+    form = CheckForm()
+
+    if form.is_submitted():
+        result = request.form.values()
+
+        a = list(result)
+        a.remove('Submit')
+        a.remove(form.D_name.data)
+        a.remove(form.P_name.data)
+
+
+        a=[int(x) for x in a]
+
+
+
+        final_features = [np.array(a)]
+
+
+        prediction=model.predict(final_features)
+        return render_template('answer.html',prediction=prediction)
+
+    # final_features = [np.array(int_features)]
+    # prediction = model.predict(final_features)
+
+    return render_template('formsection.html', form=form)
+
+
+
+if __name__ == '__main__':
+    app.run(debug=True)