import numpy as np import pandas as pd import matplotlib.pyplot as plt import plotly.express as px import seaborn as sns from sklearn.cluster import KMeans from sklearn.model_selection import train_test_split from sklearn.pipeline import make_pipeline from sklearn.preprocessing import StandardScaler from sklearn.decomposition import PCA from sklearn.preprocessing import LabelEncoder

data_df=pd.read_csv('/work/Mall_Customers.csv')

data_df.head()

print(data_df.shape) print(data_df.info())

data_df.isnull().sum()

# drop Customer id data_df = data_df.drop('CustomerID', axis=1) data_df.head(2)

plt.figure(1 , figsize = (15 , 6)) n = 0 for x in ['Age' , 'Annual Income (k$)' , 'Spending Score (1-100)']: n += 1 plt.subplot(1 , 3 , n) plt.subplots_adjust(hspace =0.5 , wspace = 0.5) sns.distplot(data_df[x] , bins = 20) plt.title('Distplot of {}'.format(x)) plt.show()

plt.figure(1 , figsize = (15 , 5)) sns.countplot(y = 'Gender' , data = data_df) plt.show()

plt.figure(1 , figsize = (15 , 7)) n = 0 for x in ['Age' , 'Annual Income (k$)' , 'Spending Score (1-100)']: for y in ['Age' , 'Annual Income (k$)' , 'Spending Score (1-100)']: n += 1 plt.subplot(3 , 3 , n) plt.subplots_adjust(hspace = 0.5 , wspace = 0.5) sns.regplot(x = x , y = y , data = data_df) plt.ylabel(y.split()[0]+' '+y.split()[1] if len(y.split()) > 1 else y ) plt.show()

train_X, test_X = train_test_split(data_df, test_size=0.2, random_state=42) print(len(train_X), "train +", len(test_X), "test")

# lets take copy of the data df = train_X.copy()

# Let fit and transform the Gender attribute into numeric le = LabelEncoder() le.fit(df.Gender) df.loc[:,'Gender'] = le.transform(df.Gender) df.head(3)

# Create scaler: scaler scaler = StandardScaler() scaler.fit(df) # transform data_scaled = scaler.transform(df) data_scaled[0]

pca = PCA() # fit PCA pca.fit(data_scaled) # PCA features features = range(pca.n_components_) # PCA transformed data data_pca = pca.transform(data_scaled) pca.explained_variance_ratio_

plt.bar(features, pca.explained_variance_ratio_) plt.xticks(features) plt.ylabel('variance') plt.xlabel('PCA feature') plt.show()

# Principal component analysis (PCA) and singular value decomposition (SVD) # PCA and SVD are closely related approaches and can be both applied to decompose any rectangular matrices. pca2 = PCA(n_components=2, svd_solver='full') # fit PCA pca2.fit(data_scaled) # PCA transformed data data_pca2 = pca2.transform(data_scaled) print(data_pca2.shape)

xs = data_pca2[:,0] ys = data_pca2[:,1] plt.scatter(ys, xs) plt.grid(False) plt.title('Scatter Plot of Customers data') plt.xlabel('PCA-01') plt.ylabel('PCA-02') plt.show()

# finding elbow value for different number of clusters. X = data_pca2 inertia = [] for n in range(1 , 11): algorithm = (KMeans(n_clusters = n ,init='k-means++',random_state= 42 ) ) algorithm.fit(X) inertia.append(algorithm.inertia_)

plt.figure(1 , figsize = (15 ,6)) plt.plot(np.arange(1 , 11) , inertia , 'o') plt.plot(np.arange(1 , 11) , inertia , '-' , alpha = 0.5) plt.xlabel('Number of Clusters') , plt.ylabel('Inertia') plt.show()

# KMeans model # 5 clusters to start with kmeans = KMeans(n_clusters=5, init='k-means++', random_state=0)

# Build pipeline pipeline = make_pipeline(scaler, pca2, kmeans) # fit the model to the scaled dataset model_fit = pipeline.fit(df) model_fit

# return a label for each data point based on their cluster labels = model_fit.predict(df) train_X['Clusters'] = labels

# Number of data points for each feature in each cluster train_X.groupby('Clusters').count()

# Scatter plot visuals with labels xs = data_pca2[:,0] ys = data_pca2[:,1] #zs = train_X.iloc[:,2] plt.scatter(ys, xs,c=labels) #plt.scatter(ys, zs, c=labels) plt.grid(False) plt.title('Scatter Plot of Customers data') plt.xlabel('PCA-01') plt.ylabel('PCA-02') plt.show()

# predict the labels le.fit(test_X.Gender) #update df2 with transformed values of gender test_X.loc[:,'Gender'] = le.transform(test_X.Gender) labels_test = model_fit.predict(test_X) test_X['Clusters'] = labels_test labels_test

# Number of data points for each feature in each cluster test_X.groupby('Clusters').count()

cluster_heatmap_df = train_X.groupby(['Clusters'])[['Age','Annual Income (k$)','Spending Score (1-100)']].median() heatcmap = sns.diverging_palette(230, 20, as_cmap=True) cluster_heatmap_df['FemaleRatio'] = train_X[train_X['Gender'] == 'Female'].groupby(['Clusters']).count()['Gender'] / train_X.groupby(['Clusters']).count()['Gender'] * 100 fig, ax = plt.subplots(1, 1, figsize=(10, 10)) sns.heatmap(cluster_heatmap_df.T, square=True, linewidth=3, vmax=80, vmin=1, cmap=heatcmap, cbar=False, annot=True, fmt='3.0f', ax=ax, ); ax.set_title('Cluster Summary'); plt.tight_layout()