def get_series(name=None):
out_dir = h.get_output_path('rag')
dfs_list = glob(out_dir + f'/*/*_{name or "all"}.csv')
if len(dfs_list) == 0:
return None
dfs = []
for df_csv in dfs_list:
df = pd.read_csv(df_csv)
df = dashboard_helpers.mapped_publisher_name(df)
df = df.groupby('publisher',
as_index=False)['weighted score ratio'].mean()
df = df.round({'weighted score ratio': 2})
df['weighted score ratio'] = df['weighted score ratio'].apply(
lambda x: x * 100)
df_date = df_csv.split('/')[-2]
df['date'] = datetime.datetime.strptime(df_date, '%Y-%m-%d')
dfs.append(df)
return dfs
def get_df_series(name=None):
out_dir = h.get_output_path('rag')
dfs_list = glob(out_dir + f'/*/*_{name or "all"}.csv')
dfs = []
for df_csv in dfs_list:
df = pd.read_csv(df_csv)
df_date = df_csv.split('/')[-2]
df['date'] = df_date
dfs.append(df)
return dfs
def transform(name, input_file=None):
if input_file is None:
file_list = traverse_output(name)
else:
try:
with open(input_file, 'r') as fp:
file_list = [line.rstrip() for line in fp]
except:
logger.warn(
f'Cannot read from list of output files at {input_file}, falling back to all collected data!'
)
file_list = traverse_output(name)
logger.debug(f'{len(file_list)} files to transform.')
catalog = Catalog()
catalog.catalog_id = "datopian_data_json_" + name
datasets_number = 0
resources_number = 0
for file_path in file_list:
data = read_file(file_path)
if not data:
continue
dataset = _transform_scraped_dataset(data, name)
catalog.datasets.append(dataset)
datasets_number += 1
resources_number += len(dataset.distribution)
logger.debug('{} datasets transformed.'.format(datasets_number))
logger.debug('{} resources transformed.'.format(resources_number))
output_path = h.get_output_path('datajson')
file_path = os.path.join(output_path, f'{name}.data.json')
with open(file_path, 'w') as output:
output.write(catalog.dump())
logger.debug(f'Output file: {file_path}')
h.upload_to_s3_if_configured(file_path, f'{name}.data.json')
import json
from pathlib import Path
import re
from collections import Counter
import hashlib
from edscrapers.cli import logger
from edscrapers.transformers.base import helpers as h
from edscrapers.scrapers.base.graph import GraphWrapper
import igraph
OUTPUT_DIR = os.getenv('ED_OUTPUT_PATH') # get the output directory
# get this transformer's output directory
CURRENT_TRANSFORMER_OUTPUT_DIR = h.get_output_path('collections')
def transform(name=None, input_file=None):
"""
function is responsible for transforming raw datasets into Collections
"""
if not name: # user has not provided a scraper name to get collections with
logger.error(
'Scraper/Office name not provided. Cannot generate collections')
sys.exit(1)
# load the Graph representing the scraped datasets
GraphWrapper.load_graph(file_dir_path=Path(OUTPUT_DIR, 'graphs', name),
file_stem_name=name)
import os
import sys
import json
import hashlib
from pathlib import Path
from collections import Counter
import re
from edscrapers.cli import logger
from edscrapers.transformers.base import helpers as h
from edscrapers.scrapers.base.graph import GraphWrapper
OUTPUT_DIR = os.getenv('ED_OUTPUT_PATH') # get the output directory
# get this transformer's output directory
CURRENT_TRANSFORMER_OUTPUT_DIR = h.get_output_path('sources')
def transform(name=None, input_file=None):
"""
function is responsible for transofrming raw datasets into Sources
"""
if not name: # user has not provided a scraper name to get collections with
logger.error(
'Scraper/Office name not provided. Cannot generate collections')
sys.exit(1)
# load the Graph representing the scraped datasets
GraphWrapper.load_graph(file_dir_path=Path(OUTPUT_DIR, 'graphs', name),
file_stem_name=f'{name}.collections')
def transform(name=None,
input_file=None,
use_raw_datasets=False) -> pd.DataFrame:
""" function transforms the datajson/datasets into
a dataframe/csv containig data to be used for RAG analyses on
the efficacy of the scraping toolkit to get viable/usable structured data from
the unstructured data source.
The function by default operates on/utilises datajson i.e.
the json that is ready to be ingested by the ckan harvester;
However, setting 'use_raw_datasets' to True means the function will
operate on the raw, parsed data which was scraped from the data source.
PARAMETERS
- name: if provided must correspond to the name of a scraper.
if 'use_raw_datasets' is False, file with the format '<name>.data.json'
will be located in the datajson subdirectory of 'ED_OUTPUT_PATH/transformers'
and read.
if 'use_raw_datasets' is True, dataset files contained in the 'name'
scrapers subdirectory of the 'ED_OUTPUT_PATH/scrapers' will be read
input_file: if provided mut be a file with list of datajson or dataset files
to read.
If no parameters are provided, which is the default behaviour;
then all datajson files contained in datajson subdirectory of
'ED_OUTPUT_PATH/transformers' will be read.
function returns the DataFrame containing the transformed datajson/dataset files
"""
file_list = [] # holds the list of files which contain datajson/dataset
datasets_list = [] # holds the data jsons gotten from files
if use_raw_datasets == True: # work on raw datasets
if not input_file: # no input file provided
# loop over directory structure
if name:
# loop over <name> scraper output e.g nces
file_list = h.traverse_output(name)
# datasets = list of all <name> files
else:
# loop over everything
file_list = h.traverse_output(None)
# datasets = list of all JSON files
else: # input file provided
# read input_file, which is a list of files
with open(input_file, 'r') as fp:
try:
file_list = [line.rstrip() for line in fp]
except Exception:
logger.warning(
f'Cannot read from list of output files at {input_file}, falling back to all collected data!'
)
file_list = h.traverse_output(None)
else: # work with processed/transformed datajson
if not input_file: # no input file provided
if name: # name of processed datajson is provided so get the file path
file_list.append(
Path(h.get_output_path('datajson'), f'{name}.data.json'))
else: # name of processed datajson not provided
file_list.extend(
Path(h.get_output_path('datajson')).glob('*.json'))
else: # input file provided
# read input_file, which is a list of files
with open(input_file, 'r') as fp:
try:
file_list = [line.rstrip() for line in fp]
except Exception:
logger.warning(
f'Cannot read from list of output files at {input_file}, falling back to all collected data!'
)
file_list.extend(
Path(h.get_output_path('datajson')).glob('*.json'))
if use_raw_datasets == True: # work on raw datasets
# read the contents in file_list
for file_path in file_list:
# read json from the file using helper
data = h.read_file(file_path)
# compute the weight score of the dataset
compute_score(data, append_score=True, use_raw_datasets=True)
datasets_list.append(data)
else: # work with processed json data
# read the contents in the file_list
for file_path in file_list:
# read json from file using helper function
data = h.read_file(file_path)
for dataset_dict in data.get(
'dataset',
[]): # loop through the datasets contained in data
# compute the weighted score of the dataset
compute_score(dataset_dict,
append_score=True,
use_raw_datasets=False)
datasets_list.append(dataset_dict)
if use_raw_datasets == True: # work on raw datasets
# map the datasets to pandas format
dataset_rows_list = map(lambda dataset: [dataset.get('publisher'),\
dataset.get('source_url'), \
dataset.get('_weighted_score'), \
dataset.get('_weighted_score_ratio')],
datasets_list)
else: # work on processed datajson
# map the dataset to pandas format
dataset_rows_list = map(lambda dataset: [dataset.get('publisher')['name'],\
dataset.get('scraped_from'), \
dataset.get('_weighted_score'), \
dataset.get('_weighted_score_ratio')],
datasets_list)
# create the pandas df
weighted_datasets_scores_df = pd.DataFrame(dataset_rows_list,
columns=[
'publisher', 'source url',
'weighted score',
'weighted score ratio'
])
# create a df that incorporates domain info
weighted_datasets_scores_df2 = pd.DataFrame(columns=['domain'])
weighted_datasets_scores_df2['domain'] = weighted_datasets_scores_df.\
apply(lambda row: urllib.parse.\
urlparse(row['source url']).hostname.\
replace('www2.', 'www.').replace('www.', ''), axis=1)
weighted_datasets_scores_df2['publisher'] = weighted_datasets_scores_df[
'publisher']
weighted_datasets_scores_df2['source url'] = weighted_datasets_scores_df[
'source url']
weighted_datasets_scores_df2[
'weighted score'] = weighted_datasets_scores_df['weighted score']
weighted_datasets_scores_df2[
'weighted score ratio'] = weighted_datasets_scores_df[
'weighted score ratio']
# create the output csv file name
output_dated_dir = os.path.join(
OUTPUT_DIR, f'{dt.now().year}-{dt.now().month}-{dt.now().day}')
Path(output_dated_dir).mkdir(parents=True, exist_ok=True)
if use_raw_datasets == True: # use raw datasets
output_filename = "datasets_weighted_scores_{}_raw.csv".format(
name or "all")
else: # use processed datajson
output_filename = "datasets_weighted_scores_{}.csv".format(name
or "all")
# create the fullpath weer file will be written
fullpath = os.path.join(OUTPUT_DIR, output_filename)
# write the dataframe to csv
weighted_datasets_scores_df2.to_csv(fullpath, index=False)
weighted_datasets_scores_df2.to_csv(os.path.join(output_dated_dir,
output_filename),
index=False)
# write the csv to S3 bucket
h.upload_to_s3_if_configured(fullpath, f'{output_filename}')
return weighted_datasets_scores_df2
""" module computes the weighted scores of data.json files and
transforms the resources into a csv file
with name 'datasets_weighted_scores_{yyyy_mm_dd}.csv' """
import urllib.parse
import os
import pandas as pd
from datetime import datetime as dt
from pathlib import Path
import edscrapers.transformers.base.helpers as h
from edscrapers.cli import logger
from edscrapers.transformers.rag import DATASET_WEIGHTING_SYS, TOTAL_WEIGHT # import weighting system & total weight
# get the output directory
OUTPUT_DIR = h.get_output_path('rag')
def transform(name=None,
input_file=None,
use_raw_datasets=False) -> pd.DataFrame:
""" function transforms the datajson/datasets into
a dataframe/csv containig data to be used for RAG analyses on
the efficacy of the scraping toolkit to get viable/usable structured data from
the unstructured data source.
The function by default operates on/utilises datajson i.e.
the json that is ready to be ingested by the ckan harvester;
However, setting 'use_raw_datasets' to True means the function will
operate on the raw, parsed data which was scraped from the data source.
def transform(name=None, input_file=None):
print(name)
file_list = [] # holds the list of files which contain datajson/dataset
datasets_list = [] # holds the data jsons gotten from files
if name: # name of processed datajson is provided so get the file path
file_list.append(Path(h.get_output_path('datajson'), f'{name}.data.json'))
else: # name of processed datajson not provided
file_list.extend(Path(h.get_output_path('datajson')).glob('*.json'))
# read the contents in the file_list
for file_path in file_list:
df = pd.DataFrame(columns=[
'title',
'description',
'tags',
'modified'
'publisher',
'source_url',
'data_steward_email',
'name',
'access_level',
'bureauCode',
'programCode',
'license',
'spatial',
'categories',
'level_of_data'
])
if name:
sheet_name = name
else:
sheet_name = file_path.name.split('.')[0].upper()
# read json from file using helper function
data = h.read_file(file_path)
for dd in data.get('dataset', []): # loop through the datasets contained in data
dfd = {
'name': dd.get('identifier', None),
'title': dd.get('title', None),
'description': dd.get('description', None),
'tags': ', '.join(dd['keyword']),
'modified': dd.get('modified', None),
'publisher': dd['publisher']['name'],
'source_url': dd['scraped_from'],
'data_steward_email': dd['contactPoint']['hasEmail'],
'access_level': dd.get('accessLevel', None),
'bureauCode': ', '.join(dd.get('bureauCode', [])),
'programCode': ', '.join(dd.get('programCode', [])),
'license': dd.get('license', None),
'spatial': dd.get('spatial', None),
'categories': ', '.join(dd.get('theme', [])),
'level_of_data': ', '.join(dd.get('levelOfData', [])),
}
# if df is None:
# # On first run, initialize the datframe with the datajson structure
# # TODO: Remove this hack, maybe, sometimes
# df = pd.DataFrame(columns=dataset_dict.keys())
# datasets_list.append(dataset_dict)
# print(dataset_dict['title'])
df2 = pd.DataFrame([dfd.values()], columns=dfd.keys())
# print(df2)
logger.debug(f"Dumping data for [{sheet_name}] {dd['identifier']}")
df = df.append(df2, ignore_index=True)
logger.debug(f"Dumping data for {file_path}")
_add_to_spreadsheet(os.path.join(OUTPUT_DIR, 'datasets.xlsx'), sheet_name, df)
import urllib.parse
import os
import pandas as pd
from datetime import datetime as dt
from pathlib import Path
import edscrapers.transformers.base.helpers as h
from edscrapers.cli import logger
# get the output directory
OUTPUT_DIR = h.get_output_path('excel')
def _add_to_spreadsheet(file_path, sheet_name, result):
# write the result (dataframe) to an excel sheet
if os.path.exists(file_path): # check if excel sheet exist
writer_mode = 'a' # set write mode to append
else:
writer_mode = 'w' # set write mode to write
with pd.ExcelWriter(file_path, engine="openpyxl",
mode=writer_mode) as writer:
result.to_excel(writer,
sheet_name=sheet_name,
index=False,
engine='openpyxl')
pass
def transform(name=None, input_file=None):
print(name)
file_list = [] # holds the list of files which contain datajson/dataset
def transform(name, input_file=None):
if input_file is None:
file_list = traverse_output(name)
else:
try:
with open(input_file, 'r') as fp:
file_list = [line.rstrip() for line in fp]
except:
logger.warning(
f'Cannot read from list of output files at {input_file}, falling back to all collected data!'
)
file_list = traverse_output(name)
logger.debug(f'{len(file_list)} files to transform.')
catalog = Catalog()
catalog.catalog_id = "datopian_data_json_" + (name or 'all')
# keep track/stata for item transformed
datasets_number = 0
resources_number = 0
sources_number = 0
collections_number = 0
# loop through the list of filepaths to be transformed
for file_path in file_list:
data = read_file(file_path)
if not data:
continue
dataset = _transform_scraped_dataset(data, name)
if not dataset: # no dataset was returned (i.e. dataset probably marked for removal)
continue
catalog.datasets.append(dataset)
datasets_number += 1
resources_number += len(dataset.distribution)
# TODO WORK FROM BELOW HERE
# get the list of Sources for this catalog
catalog_sources = list()
try:
# read the list of preprocessed (but still 'raw') Sources from file
catalog_sources = read_file(
f"{h.get_output_path('sources')}/{(name or 'all')}.sources.json")
# transform the list of preprocessed Sources to a list of Source objects acceptable for the catalog object
catalog_sources = _transform_preprocessed_sources(catalog_sources)
except:
logger.warning(
f'"sources transformer" output file ({(name or "all")}.sources.json) not found. This datajson output will have no "source" field'
)
# add the list of Source objects to the catalog
catalog.sources = catalog_sources or []
# update the number fo transformed Sources
sources_number = len(catalog_sources or [])
# get the list of Collections for this catalog
catalog_collections = list()
try:
# read the list of preprocessed (but still 'raw') Collections from file
catalog_collections = read_file(
f"{h.get_output_path('collections')}/{(name or 'all')}.collections.json"
)
# transform the list of preprocessed Collections to a list of Collection objects acceptable for the catalog object
catalog_collections = _transform_preprocessed_collections(
catalog_collections)
except:
logger.warning(
f'"sources transformer" output file ({(name or "all")}.collections.json) not found. This datajson output will have no "collection" field'
)
# add the list of Collection objects to the catalog
catalog.collections = catalog_collections or []
# update the number fo transformed Collections
collections_number = len(catalog_collections or [])
# validate the catalog object
if not catalog.validate_catalog(pls_fix=True):
logger.error(f"catalog validation Failed! Ending transform process")
return
logger.debug('{} Sources transformed.'.format(sources_number))
logger.debug('{} Collections transformed.'.format(collections_number))
logger.debug('{} datasets transformed.'.format(datasets_number))
logger.debug('{} resources transformed.'.format(resources_number))
output_path = h.get_output_path('datajson')
file_path = os.path.join(output_path, f'{(name or "all")}.data.json')
with open(file_path, 'w') as output:
output.write(catalog.dump())
logger.debug(f'Output file: {file_path}')
h.upload_to_s3_if_configured(file_path, f'{(name or "all")}.data.json')
