def vectorize(data_path, no_of_images, indicator):
'''
Takes the path, total number of folders(not images coz folders may be empty)
in path and creates vector matrix. Generlly called in Model.py file
Input: Path to files, Total Images, print step(how many images till notification)
Output: Final dataset to be used in modeling after PCA ,Index dictionary
'''
# Since some of the images may not be loaded(dont exist or other errors) we
# start a dictionary to keep track of which ones do and which ones dont
index_dict = {}
# dict_counter keeps a count of number of images successfully loaded
dict_counter = 0
predata = []
for i in xrange(no_of_images):
image_name = data_path + "{0}/{0}.jpg".format(i)
if os.path.exists(image_name):
# Get features
features = preprocess(image_name)
# Forming three matrices from all the images. these will be
# combined later
predata.append(features)
index_dict[dict_counter] = i
dict_counter += 1
else:
#index_dict[i] = "Load Error:No image"
pass
if i % indicator == 0:
print "%d images finished" % i
# Convert the two lists to np arrays
data = np.array(predata)
print data
print">>>>>>>>>>>>>>", data.shape
pickle_this(data, "Final_Feature_Matrix_For_PCA.pkl")
pickle_this(index_dict, "Image_model_Index_dict.pkl")
# Perform PCA
data = data_pca_pipeline(data)
return data, index_dict