-
Notifications
You must be signed in to change notification settings - Fork 72
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
9 changed files
with
3,488 additions
and
4 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,79 @@ | ||
{ | ||
"Credit Card Fraud Estimator": { | ||
"Average Amount per Transaction per Day": { | ||
"type": "number", | ||
"min_value": 0, | ||
"max_value": 100000, | ||
"default_value": 100, | ||
"step": 100, | ||
"field_name": "avg_amount_per_day" | ||
}, | ||
"Transaction Amount": { | ||
"type": "number", | ||
"min_value": 0, | ||
"max_value": 100000, | ||
"default_value": 3000, | ||
"step": 100, | ||
"field_name": "transaction_amount" | ||
}, | ||
"Is Declined": { | ||
"type": "dropdown", | ||
"options": [ | ||
"Yes", | ||
"No" | ||
], | ||
"default_value": "No", | ||
"field_name": "Is_declined" | ||
}, | ||
"Total Number of Declines per Day": { | ||
"type": "number", | ||
"min_value": 0, | ||
"max_value": 100, | ||
"default_value": 0, | ||
"step": 1, | ||
"field_name": "no_of_declines_per_day" | ||
}, | ||
"Is Foreign Transaction": { | ||
"type": "dropdown", | ||
"options": [ | ||
"Yes", | ||
"No" | ||
], | ||
"default_value": "No", | ||
"field_name": "Is_Foreign_transaction" | ||
}, | ||
"Is High-Risk Country": { | ||
"type": "dropdown", | ||
"options": [ | ||
"Yes", | ||
"No" | ||
], | ||
"default_value": "No", | ||
"field_name": "Is_High_Risk_country" | ||
}, | ||
"Daily Chargeback Average Amount": { | ||
"type": "number", | ||
"min_value": 0, | ||
"max_value": 10000, | ||
"default_value": 0, | ||
"step": 100, | ||
"field_name": "Daily_chargeback_avg_amt" | ||
}, | ||
"6-Month Average Chargeback Amount": { | ||
"type": "number", | ||
"min_value": 0, | ||
"max_value": 10000, | ||
"default_value": 0, | ||
"step": 100, | ||
"field_name": "six_month_avg_chbk_amt" | ||
}, | ||
"6-Month Chargeback Frequency": { | ||
"type": "number", | ||
"min_value": 0, | ||
"max_value": 100, | ||
"default_value": 0, | ||
"step": 1, | ||
"field_name": "six_month_chbk_freq" | ||
} | ||
} | ||
} |
3,076 changes: 3,076 additions & 0 deletions
3,076
models/credit_card_fraud/data/creditcardcsvpresent.csv
Large diffs are not rendered by default.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,119 @@ | ||
# importing libraries | ||
from sklearn.model_selection import train_test_split | ||
from sklearn.svm import SVC | ||
import pandas as pd | ||
import warnings | ||
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix | ||
import pandas as pd | ||
import pickle | ||
from models.credit_card_fraud.modelEvaluation import ModelEvaluation | ||
warnings.filterwarnings("ignore") | ||
|
||
|
||
# reading dataset | ||
data = pd.read_csv("models\credit_card_fraud\data\creditcardcsvpresent.csv") | ||
df = data.copy(deep=True) | ||
|
||
# df.info() | ||
|
||
# remove transaction_date all values are null | ||
# and also remove merchant id | ||
df = df.drop(columns=['Merchant_id', 'Transaction date'], axis=1) | ||
|
||
|
||
# encoding for qualitative variables | ||
code = { | ||
"N": 0, | ||
"Y": 1 } | ||
|
||
for obj in df.select_dtypes("object"): | ||
df[obj] = df[obj].map(code) | ||
|
||
# Target and Feature Identification | ||
target = "isFradulent" | ||
features = [col for col in df.columns if col != target] | ||
|
||
X = df[features] # Create a DataFrame for the features | ||
y = df[target] # Create a Series for the target | ||
|
||
|
||
# Split the dataset | ||
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) | ||
|
||
# Train SVM Classifier | ||
svm_model = SVC(kernel='rbf', class_weight='balanced', random_state=42) # RBF kernel (default) is good for non-linear problems | ||
svm_model.fit(X_train, y_train) | ||
|
||
# Make predictions | ||
y_pred = svm_model.predict(X_test) | ||
|
||
# Function to prepare input data into a DataFrame | ||
def prepare_input_data( | ||
avg_amount_per_day, | ||
transaction_amount, | ||
Is_declined, | ||
no_of_declines_per_day, | ||
Is_Foreign_transaction, | ||
Is_High_Risk_country, | ||
Daily_chargeback_avg_amt, | ||
six_month_avg_chbk_amt, | ||
six_month_chbk_freq, | ||
): | ||
# Create a DataFrame with the input data | ||
input_data = { | ||
"Average Amount/transaction/day": [avg_amount_per_day], | ||
"Transaction_amount": [transaction_amount], | ||
"Is declined": [Is_declined], | ||
"Total Number of declines/day": [no_of_declines_per_day], | ||
"isForeignTransaction": [Is_Foreign_transaction], | ||
"isHighRiskCountry": [Is_High_Risk_country], | ||
"Daily_chargeback_avg_amt": [Daily_chargeback_avg_amt], | ||
"6_month_avg_chbk_amt": [six_month_avg_chbk_amt], | ||
"6-month_chbk_freq": [six_month_chbk_freq], | ||
} | ||
|
||
return pd.DataFrame(input_data) | ||
|
||
def get_prediction( | ||
avg_amount_per_day, | ||
transaction_amount, | ||
Is_declined, | ||
no_of_declines_per_day, | ||
Is_Foreign_transaction, | ||
Is_High_Risk_country, | ||
Daily_chargeback_avg_amt, | ||
six_month_avg_chbk_amt, | ||
six_month_chbk_freq, | ||
): | ||
# Prepare the input data | ||
input_df = prepare_input_data( | ||
avg_amount_per_day, | ||
transaction_amount, | ||
Is_declined, | ||
no_of_declines_per_day, | ||
Is_Foreign_transaction, | ||
Is_High_Risk_country, | ||
Daily_chargeback_avg_amt, | ||
six_month_avg_chbk_amt, | ||
six_month_chbk_freq, | ||
) | ||
# Predict using Random Forest | ||
predicted_value = svm_model.predict(input_df) | ||
|
||
# Return "Fraud" if fraud (1), else "Not a Fraud" | ||
return "Fraud" if predicted_value[0] == 1 else "Not a Fraud" | ||
|
||
|
||
# Function to save the model | ||
def save_model(): | ||
# Save the Random Forest model | ||
model_filename = 'creditCardFraud_svc_model.pkl' | ||
with open(model_filename, 'wb') as file: | ||
pickle.dump(svm_model, file) | ||
|
||
# # Function to evaluate accuracy | ||
def get_evaluator(): | ||
evaluator = ModelEvaluation(svm_model, X_train, y_train, X_test, y_test) | ||
return evaluator | ||
|
||
# save_model() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,108 @@ | ||
import numpy as np | ||
import pandas as pd | ||
import matplotlib.pyplot as plt | ||
import seaborn as sns | ||
from sklearn.metrics import accuracy_score, confusion_matrix | ||
|
||
|
||
class ModelEvaluation: | ||
def __init__(self, model, train_X, train_Y, test_X, test_Y): | ||
self.model = model | ||
self.train_X = train_X | ||
self.train_Y = train_Y | ||
self.test_X = test_X | ||
self.test_Y = test_Y | ||
self.evaluation_matrix = pd.DataFrame( | ||
np.zeros([1, 8]), | ||
columns=[ | ||
"Train-R2", | ||
"Test-R2", | ||
"Train-RSS", | ||
"Test-RSS", | ||
"Train-MSE", | ||
"Test-MSE", | ||
"Train-RMSE", | ||
"Test-RMSE", | ||
], | ||
) | ||
self.random_column = np.random.choice( | ||
train_X.columns[train_X.nunique() >= 50], 1, replace=False | ||
)[0] | ||
|
||
def evaluate(self): | ||
pred_train = self.model.predict(self.train_X) | ||
pred_test = self.model.predict(self.test_X) | ||
|
||
self.update_evaluation_matrix(pred_train, pred_test) | ||
metrics = self.get_metrics() | ||
prediction_plot = self.plot_predictions(pred_train) | ||
error_plot = self.plot_error_terms(pred_train) | ||
|
||
# adding performance graph of the model | ||
performance_plot = self.plot_performance_graph() | ||
|
||
return metrics, prediction_plot, error_plot, performance_plot | ||
|
||
def get_metrics(self): | ||
"""Return a dictionary of evaluation metrics for easy integration.""" | ||
pred_train = self.model.predict(self.train_X) | ||
pred_test = self.model.predict(self.test_X) | ||
|
||
metrics = { | ||
"Train_R2": accuracy_score(self.train_Y, pred_train), | ||
"Test_R2": accuracy_score(self.test_Y, pred_test), | ||
"Train_RSS": np.sum(np.square(self.train_Y - pred_train)), | ||
"Test_RSS": np.sum(np.square(self.test_Y - pred_test)) | ||
} | ||
return metrics | ||
|
||
def plot_predictions(self, pred_train): | ||
# Predict on test data | ||
pred_test = self.model.predict(self.test_X) | ||
|
||
# Calculate confusion matrix | ||
cm = confusion_matrix(self.test_Y, pred_test) | ||
|
||
# Plot confusion matrix | ||
fig, ax = plt.subplots(figsize=(10, 6)) | ||
sns.heatmap(cm, annot=True, fmt="d", cmap="Blues", ax=ax) | ||
|
||
ax.set_title("Confusion Matrix") | ||
ax.set_xlabel("Predicted Labels") | ||
ax.set_ylabel("True Labels") | ||
|
||
plt.tight_layout() | ||
return fig | ||
|
||
def update_evaluation_matrix(self, pred_train, pred_test): | ||
return | ||
|
||
# making a separate function for plotting error terms | ||
def plot_error_terms(self, pred_train): | ||
fig, axes = plt.subplots(figsize=(15, 6)) | ||
|
||
# Plotting error distribution | ||
sns.histplot(self.train_Y - pred_train, bins=30, kde=True, ax=axes) | ||
axes.set_title("Error Terms Distribution") | ||
axes.set_xlabel("Errors") | ||
|
||
plt.tight_layout() | ||
return fig # returning figure the is created here | ||
|
||
def plot_performance_graph(self): | ||
# Predict on test data | ||
pred_test = self.model.predict(self.test_X) | ||
|
||
# Calculate confusion matrix | ||
cm = confusion_matrix(self.test_Y, pred_test) | ||
|
||
# Plot confusion matrix | ||
fig, ax = plt.subplots(figsize=(10, 6)) | ||
sns.heatmap(cm, annot=True, fmt="d", cmap="Blues", ax=ax) | ||
|
||
ax.set_title("Confusion Matrix") | ||
ax.set_xlabel("Predicted Labels") | ||
ax.set_ylabel("True Labels") | ||
|
||
plt.tight_layout() | ||
return fig |
Oops, something went wrong.