import pandas as pd # data processing
import numpy as np # working with arrays
import matplotlib.pyplot as plt # visualization
from termcolor import colored as cl # text customization
import itertools # advanced tools
from sklearn.preprocessing import StandardScaler # data normalization
from sklearn.model_selection import train_test_split # data split
from sklearn.tree import DecisionTreeClassifier # Decision tree algorithm
from sklearn.neighbors import KNeighborsClassifier # KNN algorithm
from sklearn.linear_model import LogisticRegression # Logistic regression algorithm
from sklearn.svm import SVC # SVM algorithm
from sklearn.ensemble import RandomForestClassifier # Random forest tree algorithm
from xgboost import XGBClassifier # XGBoost algorithm
from sklearn.metrics import confusion_matrix # evaluation metric
from sklearn.metrics import accuracy_score # evaluation metric
from sklearn.metrics import f1_score # evaluation metric
# IMPORTING DATA
df = pd.read_csv('creditcard.csv')
df.drop('Time', axis = 1, inplace = True)
print(df.head())
# EDA
# 1. Count & percentage
cases = len(df)
nonfraud_count = len(df[df.Class == 0])
fraud_count = len(df[df.Class == 1])
fraud_percentage = round(fraud_count/nonfraud_count*100, 2)
print(cl('CASE COUNT', attrs = ['bold']))
print(cl('--------------------------------------------', attrs = ['bold']))
print(cl('Total number of cases are {}'.format(cases), attrs = ['bold']))
print(cl('Number of Non-fraud cases are {}'.format(nonfraud_count), attrs = ['bold']))
print(cl('Number of Non-fraud cases are {}'.format(fraud_count), attrs = ['bold']))
print(cl('Percentage of fraud cases is {}'.format(fraud_percentage), attrs = ['bold']))
print(cl('--------------------------------------------', attrs = ['bold']))
# 2. Description
nonfraud_cases = df[df.Class == 0]
fraud_cases = df[df.Class == 1]
print(cl('CASE AMOUNT STATISTICS', attrs = ['bold']))
print(cl('--------------------------------------------', attrs = ['bold']))
print(cl('NON-FRAUD CASE AMOUNT STATS', attrs = ['bold']))
print(nonfraud_cases.Amount.describe())
print(cl('--------------------------------------------', attrs = ['bold']))
print(cl('FRAUD CASE AMOUNT STATS', attrs = ['bold']))
print(fraud_cases.Amount.describe())
print(cl('--------------------------------------------', attrs = ['bold']))
# DATA SPLIT
X = df.drop('Class', axis = 1).values
y = df['Class'].values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)
print(cl('X_train samples : ', attrs = ['bold']), X_train[:1])
print(cl('X_test samples : ', attrs = ['bold']), X_test[0:1])
print(cl('y_train samples : ', attrs = ['bold']), y_train[0:10])
print(cl('y_test samples : ', attrs = ['bold']), y_test[0:10])
# MODELING
# 1. Decision Tree
tree_model = DecisionTreeClassifier(max_depth = 4, criterion = 'entropy')
tree_model.fit(X_train, y_train)
tree_yhat = tree_model.predict(X_test)
# 2. K-Nearest Neighbors
n = 5
knn = KNeighborsClassifier(n_neighbors = n)
knn.fit(X_train, y_train)
knn_yhat = knn.predict(X_test)
# 3. Logistic Regression
lr = LogisticRegression()
lr.fit(X_train, y_train)
lr_yhat = lr.predict(X_test)
# 4. SVM
svm = SVC()
svm.fit(X_train, y_train)
svm_yhat = svm.predict(X_test)
# 5. Random Forest Tree
rf = RandomForestClassifier(max_depth = 4)
rf.fit(X_train, y_train)
rf_yhat = rf.predict(X_test)
# 6. XGBoost
xgb = XGBClassifier(max_depth = 4)
xgb.fit(X_train, y_train)
xgb_yhat = xgb.predict(X_test)
# EVALUATION
# 1. Accuracy score
print(cl('ACCURACY SCORE', attrs = ['bold']))
print(cl('------------------------------------------------------------------------', attrs = ['bold']))
print(cl('Accuracy score of the Decision Tree model is {}'.format(accuracy_score(y_test, tree_yhat)), attrs = ['bold']))
print(cl('------------------------------------------------------------------------', attrs = ['bold']))
print(cl('Accuracy score of the KNN model is {}'.format(accuracy_score(y_test, knn_yhat)), attrs = ['bold'], color = 'green'))
print(cl('------------------------------------------------------------------------', attrs = ['bold']))
print(cl('Accuracy score of the Logistic Regression model is {}'.format(accuracy_score(y_test, lr_yhat)), attrs = ['bold'], color = 'red'))
print(cl('------------------------------------------------------------------------', attrs = ['bold']))
print(cl('Accuracy score of the SVM model is {}'.format(accuracy_score(y_test, svm_yhat)), attrs = ['bold']))
print(cl('------------------------------------------------------------------------', attrs = ['bold']))
print(cl('Accuracy score of the Random Forest Tree model is {}'.format(accuracy_score(y_test, rf_yhat)), attrs = ['bold']))
print(cl('------------------------------------------------------------------------', attrs = ['bold']))
print(cl('Accuracy score of the XGBoost model is {}'.format(accuracy_score(y_test, xgb_yhat)), attrs = ['bold']))
print(cl('------------------------------------------------------------------------', attrs = ['bold']))
# 2. F1 score
print(cl('F1 SCORE', attrs = ['bold']))
print(cl('------------------------------------------------------------------------', attrs = ['bold']))
print(cl('F1 score of the Decision Tree model is {}'.format(f1_score(y_test, tree_yhat)), attrs = ['bold']))
print(cl('------------------------------------------------------------------------', attrs = ['bold']))
print(cl('F1 score of the KNN model is {}'.format(f1_score(y_test, knn_yhat)), attrs = ['bold'], color = 'green'))
print(cl('------------------------------------------------------------------------', attrs = ['bold']))
print(cl('F1 score of the Logistic Regression model is {}'.format(f1_score(y_test, lr_yhat)), attrs = ['bold'], color = 'red'))
print(cl('------------------------------------------------------------------------', attrs = ['bold']))
print(cl('F1 score of the SVM model is {}'.format(f1_score(y_test, svm_yhat)), attrs = ['bold']))
print(cl('------------------------------------------------------------------------', attrs = ['bold']))
print(cl('F1 score of the Random Forest Tree model is {}'.format(f1_score(y_test, rf_yhat)), attrs = ['bold']))
print(cl('------------------------------------------------------------------------', attrs = ['bold']))
print(cl('F1 score of the XGBoost model is {}'.format(f1_score(y_test, xgb_yhat)), attrs = ['bold']))
print(cl('------------------------------------------------------------------------', attrs = ['bold']))
# 3. Confusion Matrix
# defining the plot function
def plot_confusion_matrix(cm, classes, title, normalize = False, cmap = plt.cm.Blues):
title = 'Confusion Matrix of {}'.format(title)
if normalize:
cm = cm.astype(float) / cm.sum(axis=1)[:, np.newaxis]
plt.imshow(cm, interpolation = 'nearest', cmap = cmap)
plt.title(title)
plt.colorbar()
tick_marks = np.arange(len(classes))
plt.xticks(tick_marks, classes, rotation = 45)
plt.yticks(tick_marks, classes)
fmt = '.2f' if normalize else 'd'
thresh = cm.max() / 2.
for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
plt.text(j, i, format(cm[i, j], fmt),
horizontalalignment = 'center',
color = 'white' if cm[i, j] > thresh else 'black')
plt.tight_layout()
plt.ylabel('True label')
plt.xlabel('Predicted label')
# Compute confusion matrix for the models
tree_matrix = confusion_matrix(y_test, tree_yhat, labels = [0, 1]) # Decision Tree
knn_matrix = confusion_matrix(y_test, knn_yhat, labels = [0, 1]) # K-Nearest Neighbors
lr_matrix = confusion_matrix(y_test, lr_yhat, labels = [0, 1]) # Logistic Regression
svm_matrix = confusion_matrix(y_test, svm_yhat, labels = [0, 1]) # Support Vector Machine
rf_matrix = confusion_matrix(y_test, rf_yhat, labels = [0, 1]) # Random Forest Tree
xgb_matrix = confusion_matrix(y_test, xgb_yhat, labels = [0, 1]) # XGBoost
# Plot the confusion matrix
plt.rcParams['figure.figsize'] = (6, 6)
# 1. Decision tree
tree_cm_plot = plot_confusion_matrix(tree_matrix,
classes = ['Non-Default(0)','Default(1)'],
normalize = False, title = 'Decision Tree')
plt.savefig('tree_cm_plot.png')
plt.show()
# 2. K-Nearest Neighbors
knn_cm_plot = plot_confusion_matrix(knn_matrix,
classes = ['Non-Default(0)','Default(1)'],
normalize = False, title = 'KNN')
plt.savefig('knn_cm_plot.png')
plt.show()
# 3. Logistic regression
lr_cm_plot = plot_confusion_matrix(lr_matrix,
classes = ['Non-Default(0)','Default(1)'],
normalize = False, title = 'Logistic Regression')
plt.savefig('lr_cm_plot.png')
plt.show()
# 4. Support Vector Machine
svm_cm_plot = plot_confusion_matrix(svm_matrix,
classes = ['Non-Default(0)','Default(1)'],
normalize = False, title = 'SVM')
plt.savefig('svm_cm_plot.png')
plt.show()
# 5. Random forest tree
rf_cm_plot = plot_confusion_matrix(rf_matrix,
classes = ['Non-Default(0)','Default(1)'],
normalize = False, title = 'Random Forest Tree')
plt.savefig('rf_cm_plot.png')
plt.show()
# 6. XGBoost
xgb_cm_plot = plot_confusion_matrix(xgb_matrix,
classes = ['Non-Default(0)','Default(1)'],
normalize = False, title = 'XGBoost')
plt.savefig('xgb_cm_plot.png')
plt.show()
Write, Run & Share Python code online using OneCompiler's Python online compiler for free. It's one of the robust, feature-rich online compilers for python language, supporting both the versions which are Python 3 and Python 2.7. Getting started with the OneCompiler's Python editor is easy and fast. The editor shows sample boilerplate code when you choose language as Python or Python2 and start coding.
OneCompiler's python online editor supports stdin and users can give inputs to programs using the STDIN textbox under the I/O tab. Following is a sample python program which takes name as input and print your name with hello.
import sys
name = sys.stdin.readline()
print("Hello "+ name)
Python is a very popular general-purpose programming language which was created by Guido van Rossum, and released in 1991. It is very popular for web development and you can build almost anything like mobile apps, web apps, tools, data analytics, machine learning etc. It is designed to be simple and easy like english language. It's is highly productive and efficient making it a very popular language.
When ever you want to perform a set of operations based on a condition IF-ELSE is used.
if conditional-expression
#code
elif conditional-expression
#code
else:
#code
Indentation is very important in Python, make sure the indentation is followed correctly
For loop is used to iterate over arrays(list, tuple, set, dictionary) or strings.
mylist=("Iphone","Pixel","Samsung")
for i in mylist:
print(i)
While is also used to iterate a set of statements based on a condition. Usually while is preferred when number of iterations are not known in advance.
while condition
#code
There are four types of collections in Python.
List is a collection which is ordered and can be changed. Lists are specified in square brackets.
mylist=["iPhone","Pixel","Samsung"]
print(mylist)
Tuple is a collection which is ordered and can not be changed. Tuples are specified in round brackets.
myTuple=("iPhone","Pixel","Samsung")
print(myTuple)
Below throws an error if you assign another value to tuple again.
myTuple=("iPhone","Pixel","Samsung")
print(myTuple)
myTuple[1]="onePlus"
print(myTuple)
Set is a collection which is unordered and unindexed. Sets are specified in curly brackets.
myset = {"iPhone","Pixel","Samsung"}
print(myset)
Dictionary is a collection of key value pairs which is unordered, can be changed, and indexed. They are written in curly brackets with key - value pairs.
mydict = {
"brand" :"iPhone",
"model": "iPhone 11"
}
print(mydict)
Following are the libraries supported by OneCompiler's Python compiler
| Name | Description |
|---|---|
| NumPy | NumPy python library helps users to work on arrays with ease |
| SciPy | SciPy is a scientific computation library which depends on NumPy for convenient and fast N-dimensional array manipulation |
| SKLearn/Scikit-learn | Scikit-learn or Scikit-learn is the most useful library for machine learning in Python |
| Pandas | Pandas is the most efficient Python library for data manipulation and analysis |
| DOcplex | DOcplex is IBM Decision Optimization CPLEX Modeling for Python, is a library composed of Mathematical Programming Modeling and Constraint Programming Modeling |