Create Cust_Segmentation.py

Cust_Segmentation.py

@@ -0,0 +1,59 @@
+import random 
+import numpy as np 
+import matplotlib.pyplot as plt 
+from sklearn.cluster import KMeans 
+from sklearn.datasets.samples_generator import make_blobs 
+import pandas as pd
+from sklearn.preprocessing import StandardScaler
+from mpl_toolkits.mplot3d import Axes3D 
+
+cust_df = pd.read_csv("https://raw.githubusercontent.com/sumyak/ML-Algos-and-Techniques/master/Clustering/K-Means%20Clustering/Cust_Segmentation.csv")
+
+#data pre processing
+df = cust_df.drop('Address', axis=1)
+
+#Normalizing over the standard deviation
+X = df.values[:,1:]
+X = np.nan_to_num(X)
+Clus_dataSet = StandardScaler().fit_transform(X)
+Clus_dataSet
+
+X = df.values[:,1:]
+X = np.nan_to_num(X)
+Clus_dataSet = StandardScaler().fit_transform(X)
+Clus_dataSet
+
+#Modeling
+clusterNum = 3
+k_means = KMeans(init = "k-means++", n_clusters = clusterNum, n_init = 12)
+k_means.fit(X)
+labels = k_means.labels_
+
+
+df["Clus_km"] = labels
+df.head(5)
+
+print(df.groupby('Clus_km').mean())
+
+
+#plot
+area = np.pi * ( X[:, 1])**2  
+plt.scatter(X[:, 0], X[:, 3], s=area, c=labels.astype(np.float), alpha=0.5)
+plt.xlabel('Age', fontsize=18)
+plt.ylabel('Income', fontsize=16)
+
+plt.show()
+
+fig = plt.figure(1, figsize=(8, 6))
+plt.clf()
+ax = Axes3D(fig, rect=[0, 0, .95, 1], elev=48, azim=134)
+
+plt.cla()
+# plt.ylabel('Age', fontsize=18)
+# plt.xlabel('Income', fontsize=16)
+# plt.zlabel('Education', fontsize=16)
+ax.set_xlabel('Education')
+ax.set_ylabel('Age')
+ax.set_zlabel('Income')
+
+ax.scatter(X[:, 1], X[:, 0], X[:, 3], c= labels.astype(np.float))