def image_summary(series: pd.Series,
exif: bool = False,
hash: bool = False) -> dict:
"""
Args:
series: series to summarize
exif: extract exif information
hash: calculate hash (for duplicate detection)
Returns:
"""
image_information = series.apply(
partial(extract_image_information, exif=exif, hash=hash))
summary = {
"n_truncated":
sum([
1 for x in image_information if "truncated" in x and x["truncated"]
]),
"image_dimensions":
pd.Series(
[x["size"] for x in image_information if "size" in x],
name="image_dimensions",
),
}
image_widths = summary["image_dimensions"].map(lambda x: x[0])
summary.update(named_aggregate_summary(image_widths, "width"))
image_heights = summary["image_dimensions"].map(lambda x: x[1])
summary.update(named_aggregate_summary(image_heights, "height"))
image_areas = image_widths * image_heights
summary.update(named_aggregate_summary(image_areas, "area"))
if hash:
summary["n_duplicate_hash"] = count_duplicate_hashes(image_information)
if exif:
exif_series = extract_exif_series(
[x["exif"] for x in image_information if "exif" in x])
summary["exif_keys_counts"] = exif_series["exif_keys"]
summary["exif_data"] = exif_series
return summary
def length_summary(series: pd.Series) -> dict:
length = series.str.len()
summary = {"length": length}
summary.update(named_aggregate_summary(length, "length"))
return summary