# Add the label dummy variabls to the vector X_test_vec_lbl
# create a DataFrame with the dummy variables
dummy_df = test_lbl[["cluster_1", "cluster_2", "cluster_3", "cluster_4", "cluster_5",
"cluster_6", "cluster_7", "cluster_8", "cluster_9", "cluster_10",
"cluster_11", "cluster_12"]]
# Reshaping the dummy_df to dummy_matrices
for i, col in enumerate(dummy_df.columns):
# get the column values as a dense numpy array
col_values = dummy_df[col].values.reshape(-1, 1)
# stack the column values horizontally with the sparse matrix
X_test_vec_lbl = hstack([X_test_vec_lbl, col_values], format='csr')
# Size of X_train_vec_lbl after adding 12 dummy variables
print(X_test_vec_lbl.shape)
Preview:
downloadDownload PNG
downloadDownload JPEG
downloadDownload SVG
Tip: You can change the style, width & colours of the snippet with the inspect tool before clicking Download!
Click to optimize width for Twitter