diff --git a/__init__.pyc b/__init__.pyc index 6c0d88a..463ca25 100644 Binary files a/__init__.pyc and b/__init__.pyc differ diff --git a/q01_k_means/__init__.pyc b/q01_k_means/__init__.pyc index bff55bc..9d271dd 100644 Binary files a/q01_k_means/__init__.pyc and b/q01_k_means/__init__.pyc differ diff --git a/q01_k_means/build.py b/q01_k_means/build.py index fca565c..8ab51e8 100644 --- a/q01_k_means/build.py +++ b/q01_k_means/build.py @@ -9,8 +9,9 @@ X_train = digits.images y_train = digits.target -# Write your solution here : - - - +def k_means(X_train,y_train,cluster = 10, random_state = 9): + km = KMeans(init ="random",n_clusters =10).fit(X_train) + plt.scatter(y_train,X_train[:,0,0],c = km, s=50) + plt.show() +# Write your solution here : diff --git a/q01_k_means/build.pyc b/q01_k_means/build.pyc index fa56657..5699f8d 100644 Binary files a/q01_k_means/build.pyc and b/q01_k_means/build.pyc differ diff --git a/q01_k_means/tests/__init__.pyc b/q01_k_means/tests/__init__.pyc index f6a37b9..53d4eb7 100644 Binary files a/q01_k_means/tests/__init__.pyc and b/q01_k_means/tests/__init__.pyc differ diff --git a/q01_k_means/tests/test_q01_k_means.pyc b/q01_k_means/tests/test_q01_k_means.pyc index ac55928..299fbd3 100644 Binary files a/q01_k_means/tests/test_q01_k_means.pyc and b/q01_k_means/tests/test_q01_k_means.pyc differ diff --git a/q02_hierarchy_clustering/__init__.pyc b/q02_hierarchy_clustering/__init__.pyc index 9e9464b..071d654 100644 Binary files a/q02_hierarchy_clustering/__init__.pyc and b/q02_hierarchy_clustering/__init__.pyc differ diff --git a/q02_hierarchy_clustering/build.py b/q02_hierarchy_clustering/build.py index 2ba8b26..68f62d8 100644 --- a/q02_hierarchy_clustering/build.py +++ b/q02_hierarchy_clustering/build.py @@ -1,12 +1,18 @@ -# 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 - -digits = datasets.load_digits() -df = pd.DataFrame(scale(digits.data), index=digits.target) - -# Write your solution here : +import pandas as pd +import matplotlib.pyplot as plt +from sklearn.preprocessing import scale +from scipy.cluster import hierarchy +from sklearn import datasets + +digits = datasets.load_digits() +df = pd.DataFrame(scale(digits.data), index=digits.target) + +# Write your solution here : +def hierarchy_clustering (df): + D = hierarchy.linkage(df, 'average') + plt.figure(figsize=(25, 10)) + plt.title('Hierarchical Clustering Dendrogram') + plt.xlabel('sample index') + plt.ylabel('distance') + hierarchy.dendrogram(D,leaf_rotation=90.,leaf_font_size=8.) + plt.show() diff --git a/q02_hierarchy_clustering/build.pyc b/q02_hierarchy_clustering/build.pyc index 59f6156..ea56565 100644 Binary files a/q02_hierarchy_clustering/build.pyc and b/q02_hierarchy_clustering/build.pyc differ diff --git a/q02_hierarchy_clustering/tests/__init__.pyc b/q02_hierarchy_clustering/tests/__init__.pyc index bb41aea..dbf1e30 100644 Binary files a/q02_hierarchy_clustering/tests/__init__.pyc and b/q02_hierarchy_clustering/tests/__init__.pyc differ diff --git a/q02_hierarchy_clustering/tests/test_q02_hierarchy_clustering.pyc b/q02_hierarchy_clustering/tests/test_q02_hierarchy_clustering.pyc index d1b4567..cb8e5a8 100644 Binary files a/q02_hierarchy_clustering/tests/test_q02_hierarchy_clustering.pyc and b/q02_hierarchy_clustering/tests/test_q02_hierarchy_clustering.pyc differ