def _group_channels(url_list, order):
"""
given a list of img urls, this will group them into the same well and
site, per plate
Arguments:
-----------
order : boolean
sort channel numbers into numerical order
"""
grouped_list = []
urls = [parse.img_filename(i) for i in url_list]
tmp_df = pd.DataFrame(list(url_list), columns=["img_url"])
tmp_df["plate_name"] = [parse.plate_name(i) for i in url_list]
tmp_df["plate_num"] = [parse.plate_num(i) for i in url_list]
# get_well and get_site use the image URL rather than the full path
tmp_df["well"] = [parse.img_well(i) for i in urls]
tmp_df["site"] = [parse.img_site(i) for i in urls]
grouped_df = tmp_df.groupby(
["plate_name", "plate_num", "well", "site"])
if order is True:
# order by channel
for _, group in grouped_df:
grouped = list(group["img_url"])
channel_nums = [parse.img_channel(i) for i in grouped]
# create tuple(path, channel_number) and sort by channel_number
sort_im = sorted(zip(grouped, channel_nums),
key=lambda x: x[1])
# return only the file-paths back from the list of tuples
grouped_list.append([i[0] for i in sort_im])
elif order is False:
for _, group in grouped_df:
grouped_list.append(list(group["img_url"]))
else:
raise ValueError("order needs to be a boolean")
return grouped_list
def keep_channels(img_list, channels):
"""
given a list of image paths, this will keep specified channel numbers,
and remove all others.
Parameters:
-----------
img_list : list
list of image URLs
channels : list of integers
list of channel numbers to keep
Returns:
--------
list of image URLs
"""
# find if img_urls are full paths or just filenames
if utils.is_full_path(img_list[0]):
just_file_path = [parse.img_filename(i) for i in img_list]
else:
just_file_path = img_list
channel_nums = [parse.img_channel(i) for i in just_file_path]
# make sure we zip the original img_list, *not* just_file_path
ch_img_tup = zip(channel_nums, img_list)
filtered_tup = [i for i in ch_img_tup if i[0] in channels]
_, img_urls = zip(*filtered_tup)
return img_urls
def test_ImageDict_keep_channels():
channels_to_keep = [1, 2, 3]
ImgDict = image_prep.ImageDict()
ans = ImgDict.keep_channels(IMG_URLS, channels_to_keep)
# parse channel numbers out of ans
img_names = [parse.img_filename(f) for f in ans]
img_channels = [parse.img_channel(name) for name in img_names]
for channel in img_channels:
assert channel in channels_to_keep
def test_ImageDict_remove_channels():
channels_to_remove = [4, 5]
ImgDict = image_prep.ImageDict()
ans = ImgDict.remove_channels(IMG_URLS, channels_to_remove)
# parse channel numbers out of ans
img_names = [parse.img_filename(f) for f in ans]
img_channels = [parse.img_channel(name) for name in img_names]
for channel in img_channels:
assert channel not in channels_to_remove
def _well_site_table(img_list):
"""return pandas dataframe with metadata columns"""
final_files = [_parse.img_filename(i) for i in img_list]
df_img = _pd.DataFrame({
"img_paths":
img_list,
"Metadata_well": [_parse.img_well(i) for i in final_files],
"Metadata_site": [_parse.img_site(i) for i in final_files]
})
return df_img
def get_wells(img_list, wells_to_get, plate=None):
"""
given a list of image paths, this will return the images matching
the well or wells given in well
Parameters:
-----------
img_list : list
list of image URLs
well : string or list of strings
which well(s) to select
plate: string or list of strings (default = None)
get wells per specified plate(s)
"""
# parse wells from metadata
if plate is None:
# ignore plate labels, get all matching wells
wells = [parse.img_well(path) for path in img_list]
combined = zip(img_list, wells)
if isinstance(wells_to_get, list):
wanted_images = []
for i in wells_to_get:
for path, parsed_well in combined:
if i == parsed_well:
wanted_images.append(path)
elif isinstance(wells_to_get, str):
wanted_images = []
for path, parsed_well in combined:
if wells_to_get == parsed_well:
wanted_images.append(path)
return wanted_images
else:
# get wells per specified plate(s)
wanted_images = []
if isinstance(wells_to_get, str):
wells_to_get = [wells_to_get]
if isinstance(plate, str):
plate = [plate]
urls = [parse.img_filename(i) for i in img_list]
tmp_df = pd.DataFrame(list(img_list), columns=["img_url"])
tmp_df["plate_name"] = [parse.plate_name(i) for i in img_list]
tmp_df["well"] = [parse.img_well(i) for i in urls]
tmp_df["site"] = [parse.img_site(i) for i in urls]
grouping_cols = ["plate_name"]
grouped_df = tmp_df.groupby(grouping_cols)
for name, group in grouped_df:
if name in plate:
# get only wells that match well
tmp_urls = group[group.well.isin(
wells_to_get)].img_url.tolist()
wanted_images.extend(tmp_urls)
return wanted_images
def create_long_loaddata(img_list):
"""
create a dataframe of image paths with metadata columns
"""
just_filenames = [_parse.img_filename(i) for i in img_list]
df_img = _pd.DataFrame({
"URL":
just_filenames,
"path": [_parse.path(i) for i in img_list],
"Metadata_platename": [_parse.plate_name(i) for i in img_list],
"Metadata_well": [_parse.img_well(i) for i in just_filenames],
"Metadata_site": [_parse.img_site(i) for i in just_filenames],
"Metadata_channel": [_parse.img_channel(i) for i in just_filenames],
"Metadata_platenum": [_parse.plate_num(i) for i in img_list]
})
return df_img
def test_img_channel():
filename = parse.img_filename(EXAMPLE_PATH)
new_filename = parse.img_filename(NEW_EXAMPLE_PATH)
assert parse.img_channel(filename) == 1
assert parse.img_channel(new_filename) == 1
def test_img_site():
filename = parse.img_filename(EXAMPLE_PATH)
new_filename = parse.img_filename(NEW_EXAMPLE_PATH)
assert parse.img_site(filename) == 1
assert parse.img_site(new_filename) == 1
def test_img_well():
filename = parse.img_filename(EXAMPLE_PATH)
new_filename = parse.img_filename(NEW_EXAMPLE_PATH)
assert parse.img_well(filename) == "B02"
assert parse.img_well(new_filename) == "B02"
def test_img_filename():
expected = "val screen_B02_s1_w1_thumb62D4A363-7C7E-40D0-8A9E-55EC6681574D.tif"
assert parse.img_filename(EXAMPLE_PATH) == expected
assert parse.img_filename(NEW_EXAMPLE_PATH) == expected