Commit Live PR

q01_k_means/build.py

@@ -1,16 +1,43 @@
+# %load q01_k_means/build.py
 # Default imports
 from sklearn.cluster import KMeans
 import matplotlib.pyplot as plt
 from sklearn import datasets
-
+import pandas as pd
+import numpy as np
+import time
+import seaborn as sns
 
 digits = datasets.load_digits()
 
 X_train = digits.images
 y_train = digits.target
-
+print(X_train.shape)
+print(y_train.shape)
 # Write your solution here :
 
 
+def k_means(X_train,y_train,cluster=10,random_state=9):
+    X = np.reshape(X_train, (len(X_train), -1))
+    data=X
+    for i in range(cluster):
+        #print(i)
+
+        km = KMeans(init="random", n_clusters=i+1)
+        #y=km.fit_predict(X)
+        #print(y)
+        labels =km.fit_predict(data)
+        #end_time = time.time()
+        palette = sns.color_palette('deep', np.unique(labels).max() + 1)
+        colors = [palette[x] if x >= 0 else (0.0, 0.0, 0.0) for x in labels]
+        plt.scatter(data.T[0], data.T[1])
+        frame = plt.gca()
+        frame.axes.get_xaxis().set_visible(False)
+        frame.axes.get_yaxis().set_visible(False)
+        #plt.title('Clusters found by {}'.format(str(algorithm.__name__)), fontsize=24)
+        #plt.text(5, 10, 'Clustering took {:.2f} s'.format(end_time - start_time), fontsize=14)
+        plt.show()
+
 
 
+#k_means(X_train,y_train,cluster=10,random_state=9)

q02_hierarchy_clustering/build.py

@@ -1,12 +1,53 @@
+# %load q02_hierarchy_clustering/build.py
 # Default imports
 
 import pandas as pd
 import matplotlib.pyplot as plt
 from sklearn.preprocessing import scale
 from scipy.cluster import hierarchy
 from sklearn import datasets
+from scipy.cluster.hierarchy import dendrogram, linkage
 
 digits = datasets.load_digits()
 df = pd.DataFrame(scale(digits.data), index=digits.target)
 
+#print(df.head)
 # Write your solution here :
+
+def hierarchy_clustering(df):
+    Z_single = linkage(df, 'single')
+    Z_avg = linkage(df, 'average')
+    z_ward=linkage(df, 'ward')
+    z_comp=linkage(df,'complete')
+    plt.figure(figsize=(25, 10))
+    plt.title('Hierarchical Clustering Dendrogram')
+    plt.xlabel('sample index')
+    plt.ylabel('distance')
+    plt.subplot(1,2,1)
+
+    dendrogram(
+        Z_single,
+        leaf_rotation=90.,  # rotates the x axis labels
+        leaf_font_size=8.,  # font size for the x axis labels
+    )
+    plt.subplot(2,2,1)
+    dendrogram(
+        z_comp,
+        leaf_rotation=90.,  # rotates the x axis labels
+        leaf_font_size=8.,  # font size for the x axis labels
+    )
+    plt.subplot(2,2,2)
+    dendrogram(
+        Z_avg,
+        leaf_rotation=90.,  # rotates the x axis labels
+        leaf_font_size=8.,  # font size for the x axis labels
+    )
+    plt.subplot(1,2,2)
+    dendrogram(
+        z_ward,
+        leaf_rotation=90.,  # rotates the x axis labels
+        leaf_font_size=8.,  # font size for the x axis labels
+    )
+    plt.show()
+
+#hierarchy_clustering(df)