def dimensionality_reduction(data_matrix,
image_ids,
args,
label=None,
viz=False):
if args.lsa_model == "SVD":
reduced_data = reduce_dimensions_svd(data_matrix, args.k_features,
image_ids, viz)
elif args.lsa_model == "PCA":
reduced_data = reduce_dimensions_pca(data_matrix, args.k_features,
image_ids, viz)
elif args.lsa_model == "NMF":
if args.model == "CM":
print("NMF is not applicable to Color Moments")
return
reduced_data = reduce_dimensions_nmf(data_matrix, args.k_features,
image_ids, viz)
elif args.lsa_model == "LDA":
if args.model == "CM":
print("LDA is applicable only to a modified Color Moments.")
data_matrix_cmlda = convert_data_matrix_cmlda(data_matrix)
reduced_data = reduce_dimensions_lda(data_matrix_cmlda,
args.k_features, image_ids,
viz)
else:
reduced_data = reduce_dimensions_lda(data_matrix, args.k_features,
image_ids, viz)
insert_reduced_features(args.model, reduced_data, image_ids, label)
return reduced_data, image_ids
def ex_dimensionality_reduction(data_matrix,
image_ids,
model,
lsa_model,
k_features,
label=None,
viz=False):
if lsa_model == "SVD":
reduced_data = reduce_dimensions_svd(data_matrix, k_features, viz)
elif lsa_model == "PCA":
reduced_data = reduce_dimensions_pca(data_matrix, k_features, viz)
elif lsa_model == "NMF":
if model == "CM":
print("NMF is not applicable to Color Moments")
return
reduced_data = reduce_dimensions_nmf(data_matrix, k_features, viz)
elif lsa_model == "LDA":
if model == "CM":
print("LDA is modified and applicable to Color Moments")
data_matrix_cmlda = convert_data_matrix_cmlda(data_matrix)
reduced_data = reduce_dimensions_lda(data_matrix_cmlda, k_features,
viz)
else:
reduced_data = reduce_dimensions_lda(data_matrix, k_features, viz)
insert_reduced_features(model, reduced_data, image_ids, label)
if extra_credit:
return reduced_data, image_ids
def get_V_matrix(data_matrix, image_ids, args, label=None, viz=False):
if args.lsa_model == "SVD":
reduced_data, V_matrix = reduce_dimensions_svd(data_matrix,
args.k_features,
get_v=True)
elif args.lsa_model == "PCA":
reduced_data, V_matrix = reduce_dimensions_pca(data_matrix,
args.k_features,
get_v=True)
elif args.lsa_model == "NMF":
if args.model == "CM":
print("NMF is not applicable to Color Moments")
return
reduced_data, V_matrix = reduce_dimensions_nmf(data_matrix,
args.k_features,
get_v=True)
elif args.lsa_model == "LDA":
if args.model == "CM":
print("LDA is NOT applicable because of the Bag Of Word model.")
# data_matrix_cmlda = convert_data_matrix_cmlda(data_matrix)
# V_matrix = reduce_dimensions_lda(data_matrix_cmlda, args.k_features, image_ids, viz, get_v=True)
return
else:
reduced_data, V_matrix = reduce_dimensions_lda(data_matrix,
args.k_features,
get_v=True)
# insert_reduced_features(args.model, reduced_data, image_ids, label)
return reduced_data, V_matrix