Khyati Mahendru KhyatiMahendru

## creditcardfrauddetection.ipynb

      
              1 file
            
          
              3 forks
            
          
              0 comments
            
          
              3 stars
            
          
                KhyatiMahendru
                / creditcardfrauddetection.ipynb
            
            
              Last active
              February 21, 2022 16:37
            
              
                CreditCardFraudDetection.ipynb
              
          
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## mtcars_regression.py
# import dataset
import pandas as pd
data = pd.read_csv('mtcars.csv')

# remove string and categorical variables
cat_var = ['model', 'cyl', 'vs', 'am', 'gear', 'carb']
data = data.drop(cat_var, axis = 1)

# scale the variables to prevent coefficients from becoming too large or too small
from sklearn.preprocessing import MinMaxScaler

## OLS.py
import statsmodels.api as sm
model = sm.OLS(y, X[:, 4]).fit()
model.summary()

## generate_regression_data.py
from sklearn.datasets import make_regression
X, y = make_regression(n_samples = 20, n_features = 6, random_state = 2, noise = 0.5)

## decisiontree_entropy.py
from sklearn.tree import DecisionTreeClassifier
clf_entropy = DecisionTreeClassifier(criterion = 'entropy', random_state = 33)
clf_entropy.fit(X, Y)

## decisiontree_gini.py
from sklearn.tree import DecisionTreeClassifier
clf_gini = DecisionTreeClassifier(criterion = 'gini', random_state = 33)
clf_gini.fit(X, Y)

## silhouette_score.py
from sklearn.metrics import silhouette_score

sil = []
kmax = 10

# dissimilarity would not be defined for a single cluster, thus, minimum number of clusters should be 2
for k in range(2, kmax+1):
  kmeans = KMeans(n_clusters = k).fit(x)
  labels = kmeans.labels_
  sil.append(silhouette_score(x, labels, metric = 'euclidean'))

## elbow_method.py
from sklearn.cluster import KMeans

# function returns WSS score for k values from 1 to kmax
def calculate_WSS(points, kmax):
  sse = []
  for k in range(1, kmax+1):
    kmeans = KMeans(n_clusters = k).fit(points)
    centroids = kmeans.cluster_centers_
    pred_clusters = kmeans.predict(points)
    curr_sse = 0

## generate_clustering_data.py
from sklearn.datasets import make_blobs

# Create dataset with 3 random cluster centers and 1000 datapoints
x, y = make_blobs(n_samples = 1000, centers = 3, n_features=2, shuffle=True, random_state=31)

## model_KL.py
# importing requirements
from keras.layers import Dense
from keras.models import Sequential
from keras.optimizers import adam

# alpha = 0.001 as given in the lr parameter in adam() optimizer

# build the model
model_alpha1 = Sequential()
model_alpha1.add(Dense(50, input_dim=2, activation='relu'))
	# import dataset
	import pandas as pd
	data = pd.read_csv('mtcars.csv')

	# remove string and categorical variables
	cat_var = ['model', 'cyl', 'vs', 'am', 'gear', 'carb']
	data = data.drop(cat_var, axis = 1)

	# scale the variables to prevent coefficients from becoming too large or too small
	from sklearn.preprocessing import MinMaxScaler
	import statsmodels.api as sm
	model = sm.OLS(y, X[:, 4]).fit()
	model.summary()
	from sklearn.datasets import make_regression
	X, y = make_regression(n_samples = 20, n_features = 6, random_state = 2, noise = 0.5)
	from sklearn.tree import DecisionTreeClassifier
	clf_entropy = DecisionTreeClassifier(criterion = 'entropy', random_state = 33)
	clf_entropy.fit(X, Y)
	from sklearn.tree import DecisionTreeClassifier
	clf_gini = DecisionTreeClassifier(criterion = 'gini', random_state = 33)
	clf_gini.fit(X, Y)
	from sklearn.metrics import silhouette_score

	sil = []
	kmax = 10

	# dissimilarity would not be defined for a single cluster, thus, minimum number of clusters should be 2
	for k in range(2, kmax+1):
	kmeans = KMeans(n_clusters = k).fit(x)
	labels = kmeans.labels_
	sil.append(silhouette_score(x, labels, metric = 'euclidean'))
	from sklearn.cluster import KMeans

	# function returns WSS score for k values from 1 to kmax
	def calculate_WSS(points, kmax):
	sse = []
	for k in range(1, kmax+1):
	kmeans = KMeans(n_clusters = k).fit(points)
	centroids = kmeans.cluster_centers_
	pred_clusters = kmeans.predict(points)
	curr_sse = 0
	from sklearn.datasets import make_blobs

	# Create dataset with 3 random cluster centers and 1000 datapoints
	x, y = make_blobs(n_samples = 1000, centers = 3, n_features=2, shuffle=True, random_state=31)
	# importing requirements
	from keras.layers import Dense
	from keras.models import Sequential
	from keras.optimizers import adam

	# alpha = 0.001 as given in the lr parameter in adam() optimizer

	# build the model
	model_alpha1 = Sequential()
	model_alpha1.add(Dense(50, input_dim=2, activation='relu'))