Scribd
Upload
11 views2 pages

Slip Clustering

Uploaded by

prime04072001
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
11 views2 pages

Slip Clustering

Uploaded by

prime04072001
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

#Clustering

# normalize data
from sklearn.cluster import KMeans
cluster_range = range(1, 10)
cluster_errors = []
#elbow method to find best no. of clusters
for num_clusters in cluster_range:
clusters = KMeans(num_clusters, n_init="auto")
clusters.fit(scaled_df)
cluster_errors.append(clusters.inertia_)
plt.plot(cluster_range, cluster_errors, marker = "o")
#got k from plot
k=3
clusters = KMeans(k, random_state = 42, n_init="auto")
clusters.fit(scaled_df)
df["clusterid"] = clusters.labels_
# clusters.cluster_centers_
# clusters.labels_
#ROC Curve
from sklearn import metrics
def draw_roc_curve( model, test_X, test_y ):
test_results_df = pd.DataFrame( { 'actual': test_y } )
test_results_df = test_results_df.reset_index()
predict_proba_df = pd.DataFrame( model.predict_proba( test_X.values
))
test_results_df['chd_1'] = predict_proba_df.iloc[:,1:2]
fpr, tpr, thresholds = metrics.roc_curve(
test_results_df.actual,test_results_df.chd_1,drop_intermediate = False )
auc_score = metrics.roc_auc_score( test_results_df.actual,
test_results_df.chd_1 )
plt.plot(fpr, tpr, label = 'ROC curve (area = %0.2f)' % auc_score)
plt.plot([0, 1], [0, 1], 'k--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
#PCA
from sklearn.preprocessing import StandardScaler
from numpy.linalg import eig

X_norm = StandardScaler().fit_transform(X)
X_norm = pd.DataFrame(X_norm, columns=feat)
X_mean_adj = X_norm - X_norm.mean()
cov_mat = X_mean_adj.cov()
val, vec = eig(cov_mat)
val = np.array(val)
vec = np.array(vec)
sorted_idx = np.argsort(-val)
val = val[sorted_idx]
vec = vec[:, sorted_idx]
pc1 = np.dot(vec[:, 0], X_mean_adj.T)

from sklearn.decomposition import PCA


pca = PCA(n_components=2)
principle_components = pca.fit_transform(X_norm)
principle_components

You might also like