def load(self):
# Most of reference sequences are short enough to not be split
self.annotation_file = self.refdata.get_sequence_dict()["annotation"]
print(f"Using the annotation file: '{self.annotation_file}'")
self.annotation_df = load_tsv(self.annotation_file)
print(f"Loaded annotation table with shape {self.annotation_df.shape}")
self._annotation_df = self.annotation_df.copy()
self.raw_nucleotide_fasta_headers = self.annotation_df[
"former_id"].values.tolist()
_namespace.separator,
_namespace.output_file,
)
if __name__ == '__main__':
(
target_file,
target_column_name,
source_table_file,
source_column_names,
separator,
out_file,
) = _parse_args()
source_df = load_tsv(source_table_file)
source_sub_df = pd.DataFrame()
source_sub_df["target"] = source_df[target_column_name].copy()
source_sub_df["source"] = source_df.loc[:, source_column_names].fillna(
"").agg(separator.join, axis=1)
source_sub_df = source_sub_df.loc[
source_sub_df["source"].map(lambda x: len(x) > 0), :]
target_string = load_string(target_file)
collector_string = str(target_string)
counter = 0
for source, target in source_sub_df.values:
collector_string = collector_string.replace(str(source), target)
counter += 1
choices=["inner", "outer"],
help="(Optional) How to handle indexes on other axis (or axes)")
parser.add_argument("-o", "--output", required=True, help="Output table")
_namespace = parser.parse_args()
return _namespace.input, _namespace.axis, _namespace.index, _namespace.join, _namespace.output
if __name__ == '__main__':
input_tables, axis, index, join, output_table = parse_args()
table_files = remove_empty_values(
[i for i in input_tables if is_file_valid(i)])
if len(table_files) == 0:
raise ValueError("No valid tables!")
dataframes = []
for table_file in table_files:
dataframe = load_tsv(table_file)
if dataframe.shape[0] == 0:
continue
dataframe[PATH_COL_NAME] = table_file
dataframes.append(dataframe)
is_index = len(index) > 0
if is_index:
for dataframe in dataframes:
dataframe.set_index(index, inplace=True)
print(
f"Concatenate {len(dataframes)} dataframes with the shapes: {[i.shape for i in dataframes]}"
)
start = perf_counter()
out_df = pd.concat(dataframes,
required=True,
help="File with text to perform replacements")
parser.add_argument("-t",
"--table",
required=True,
help="Table with values to fetch")
parser.add_argument("-o", "--output", required=True, help="Output file")
_namespace = parser.parse_args()
return _namespace.input, _namespace.table, _namespace.output
if __name__ == '__main__':
text_file, combined_blast_result_file, out_file = parse_args()
text_content = load_string(text_file)
combined_blast_result_df = load_tsv(combined_blast_result_file).set_index(
"geninfo_id")
print(
f"Loaded replacer table with the shape {combined_blast_result_df.shape}"
)
renaming_dict = combined_blast_result_df["strain"].map(
lambda x: str(x).strip()).to_dict()
text_content_replaced = re.sub("\.(gbk|gff)", "", text_content)
counter = 0
for renaming_key, renaming_value in renaming_dict.items():
text_content_replaced = text_content_replaced.replace(
*[str(i) for i in [renaming_key, renaming_value]])
counter += 1
print(f"{counter} replacements were performed")
required=True,
help="Output file")
_namespace = parser.parse_args()
return (_namespace.rgi_dir, _namespace.card_version, _namespace.nbee_dir,
_namespace.output_file)
if __name__ == '__main__':
(rgi_dir, card_version, nbee_dir, out_file) = _parse_args()
# RGI
rgi_tables = find_file_by_tail(dir_name=rgi_dir,
multiple=True,
tail=".txt")
merged_rgi_df = pd.DataFrame()
for rgi_table in rgi_tables:
rgi_df = load_tsv(rgi_table)
if rgi_df.shape[0] == 0:
continue
rgi_df = remove_longest_columns(rgi_df, CELL_SIZE_LIMIT)
columns = rgi_df.columns.tolist()
rgi_df["sample_name"] = filename_only(rgi_table)
rgi_df = rgi_df.loc[:, ["sample_name"] + columns]
print(
f"Concatenate dataframes with shapes {rgi_df.shape}, {merged_rgi_df.shape}"
)
merged_rgi_df = pd.concat([merged_rgi_df, rgi_df],
axis=0,
ignore_index=True)
reference_name = "_".join(remove_empty_values(["card", card_version]))
print(f"Finished concatenating tables for '{reference_name}'")
sheets = {reference_name: merged_rgi_df}