def test_export_to_file(self):
p = spark_df_profiling_optimus.ProfileReport(self.df)
filename = os.path.join(self.test_dir, "profile_%s.html" % hash(self))
p.to_file(outputfile=filename)
self.assertLess(200,os.path.getsize(filename))
def profiler(self):
"""
This function calls the ProfileReport method from spark-df-profiling-optimus,
it gets the current DF in the analyzer and them returns the HTML profile"
:return: Profile of the DF in HTML format embedded in the Notebook
"""
df_profiler = self._df
return spark_df_profiling_optimus.ProfileReport(df_profiler)
import pandas as pd
import spark_df_profiling_optimus
if __name__ == "__main__":
import argparse
import webbrowser
parser = argparse.ArgumentParser(
description=
'Profile the variables in a CSV file and generate a HTML report.')
parser.add_argument("inputfile", help="CSV file to profile")
parser.add_argument("-o",
"--output",
help="Output report file",
default=spark_df_profiling_optimus.DEFAULT_OUTPUTFILE)
parser.add_argument("-s",
"--silent",
help="Only generate but do not open report",
action="store_true")
args = parser.parse_args()
df = pd.read_csv(args.inputfile, sep=None, parse_dates=True)
p = spark_df_profiling_optimus.ProfileReport(df)
p.to_file(outputfile=args.output)
if not args.silent:
webbrowser.open_new_tab(p.file.name)