picked = clean[clean['oz'] == 1]
nonfeatures = drop_columns(picked, drop_cols)
features = picked.columns
## standardize
standardize = StandardScaler()
X, features = picked.values, picked.columns.values
X = standardize.fit_transform(X)
## build model
cluster_labels = pd.DataFrame()
for k in range(6, 7):
pax = Clusterer(model, n_clusters=k, random_state=24)
centers = pax.fit(X)
pax.store_features(features)
print("{} grouped {} clusters.".format(model, np.shape(centers)[0]))
## update labels and scores for column k
filepath = "{}/{}/labels.pkl".format(data, model)
with open(filepath, "rb") as f:
k = pax.attributes['n_clusters']
model_labels_df = pickle.load(f)
model_labels_df["k={}".format(k)] = pax.attributes['labels_']
model_labels_df["k{}silhouette_score".format(
k)] = pax.get_silhouette_samples()
model_labels_df.to_pickle(filepath)
print("Updated labels @ {}".format(filepath))
### !
filepath = "{}/{}/estimator.pkl".format(data, model)
