def stratified_plot_scree_plot():
dataset = db["stratified_sampled"].find({}, {"_id": False})
labelled_dataset = label_categorical_data(dataset, categoric_meta_)
pca_data = pca_reduction(labelled_dataset, categories)
print("Done with pca")
pca_squared_loadings = pca_data["pca_squared_loadings"]
print("plotting scree plot")
plot_scree(pca_squared_loadings, categories)
def do_pca():
types = ["stratified"]
for type in types:
dataset = db[type + "_sampled"].find({}, {"_id": False})
labelled_dataset = label_categorical_data(dataset, categoric_meta_)
pca_data = pca_reduction(labelled_dataset, categories)
top_three_features = pca_data["features"]
insert_pca_to_mongo(top_three_features, type)
def plot_k_means_elbow():
print("K-means optimization using elbow method")
dataset = data_collection.find({}, {"_id": False})
print("Read data formatting it.")
dataset_formatted = format_dataset(dataset)
print("Finished formatting data")
labelled_dataset = np.array(
label_categorical_data(dataset_formatted, categoric_meta_))
print("Labelled Data done ! ")
elbow(labelled_dataset)
def do_mds():
mds_types = ["euclidean", "correlation"]
types = ["random", "stratified"]
for type in types:
dataset = db[type + "_pca_reduced_data"].find({}, {"_id": False})
labelled_dataset = label_categorical_data(dataset, categoric_meta_)
for mds_type in mds_types:
mds_scaled_dataset = mds_reduction(labelled_dataset, mds_type)
insert_mds_to_mongo(list(mds_scaled_dataset), mds_type, type)
def random_plot_scree_plot():
dataset = db["random_sampled"].find({}, {"_id": False})
labelled_dataset = label_categorical_data(dataset, categoric_meta_)
pca_data = pca_reduction(labelled_dataset, categories)
pca_squared_loadings = pca_data["pca_squared_loadings"]
plot_scree(pca_squared_loadings, categories)
def plot_pca():
dataset = db["stratified_sampled"].find({}, {"_id": False})
labelled_dataset = label_categorical_data(dataset, categoric_meta_)
draw_pca_plot(labelled_dataset)