how to import state of pandas dataframe to second .py file

Question

so, toward the end of my first file; we'll call /file.py.

def get_excel_data(self):
        """Places excel data into pandas dataframe"""

        # excel_data = pandas.read_excel(self.find_file())

        for extracted_archive in self.find_file():
            excel_data = pandas.read_excel(extracted_archive)

            # print(excel_data)

            columns = pandas.DataFrame(columns=excel_data.columns.tolist())
            excel_data = pandas.concat([excel_data, columns])

            excel_data.columns = excel_data.columns.str.strip()
            excel_data.columns = excel_data.columns.str.replace("/", "_")
            excel_data.columns = excel_data.columns.str.replace(" ", "_")

            total_records = 0
            num_valid_records = 0
            num_invalid_records = 0

            for row in excel_data.itertuples():
                mrn = row.MRN
                total_records += 1

                if mrn in ("", " ", "N/A", "NaT", "NaN", None) or math.isnan(mrn):
                    # print(f"Invalid record: {row}")
                    num_invalid_records += 1
                    # total_invalid = num_invalid_records + dup_count
                    excel_data = excel_data.drop(excel_data.index[row.Index])
                    # continue
                else:
                    # print(mrn) # outputs all MRN ids
                    for row in excel_data.itertuples():
                        num_valid_records += 1

                        continue   

            with open("./logs/metrics.csv", "a", newline="\n") as f:
                csv_writer = DictWriter(f, ['date', 'total_records', 'processed', 'skipped', 'success_rate'])
                # csv_writer.writeheader()

                currentDT = datetime.datetime.now()
                success_rate = num_valid_records / total_records * 100
                csv_writer.writerow(dict(date=currentDT,
                                        total_records=total_records,
                                        processed=num_valid_records,
                                        skipped=num_invalid_records,
                                        success_rate=num_valid_records / total_records * 100))

            return self.clean_data_frame(excel_data)

    def clean_data_frame(self, data_frame):
        """Cleans up dataframes"""
        for col in data_frame.columns:
            if "date" in col.lower():
                data_frame[col] = pandas.to_datetime(data_frame[col],
                                                     errors='coerce', infer_datetime_format=True)
                data_frame[col] = data_frame[col].dt.date
        data_frame['MRN'] = data_frame['MRN'].astype(int).astype(str)

        return data_frame

    def get_mapping_data(self):
        map_data = pandas.read_excel(config.MAPPING_DOC, sheet_name='main')
        columns = pandas.DataFrame(columns=map_data.columns.tolist())
        return pandas.concat([map_data, columns])

in my second file I would like to keep that end state; and do another iteration for instance.... second_file.py

def process_records(self, records, map_data, completed=None, errors=None):
    """Code to execute after webdriver initialization."""
    series_not_null = False
    try:
        num_attempt = 0

        for record in data_frame.itertuples(): # not working
            print(record)
            series_not_null = True
            mrn = record.MRN

            self.navigate_to_search(num_attempt)
            self.navigate_to_member(mrn)
            self.navigate_to_assessment()
            self.add_assessment(record, map_data)
            self.driver.switch_to.parent_frame() # not working
            sleep(.5)

            error_flag = self.close_member_tab(self.driver, mrn, error_flag)

    except Exception as exc:
        if series_not_null:
            errors = self.process_series_error(exc)

    return completed, error

both have import pandas

Answer 1

Use Dataframe.to_pickle and pandas.read_pickle:

To persist

df.to_pickle('./dataframe.pkl')

To load

df = pd.read_pickle('./dataframe.pkl')

Answer 2

you can save your dataframe in a pickle file like this. it is also worth noting that you can store most anything in a pickle file. here is a link to some info here: pickle info

import pandas as pd
import pickle

x = pd.DataFrame({'a':[1,2,3],'b':[4,5,6],'c':[7,8,9]})

#this will create a file called pickledata.p that will store the data frame
with open('pickledata.p', 'wb') as fh:   #notice that you need the 'wb' for the dump
    pickle.dump(x, fh)

#to load the file do this
with open('pickledata.p', 'rb') as fh:   #you need to use 'rb' to read
    df = pickle.load(fh)

#you can now use df like a normal dataframe
print(df)

you dont actually need the '.p' extension for a pickle file, i just like it.

so you save your dataframe at the end of script one, and then load it in at the start of script 2.