timeseries_data_generator.py

import numpy as np
import pandas as pd


class TimeseriesGenerator:
    def __init__(
        self,
        start_date: str,
        end_date: str,
        frequency: str = "H",
        dt_column: str = "timestamp",
        nr_column: str = "value",
        min_value: int = 0,
        max_value: int = 100,
    ) -> None:
        self.start_date = start_date
        self.end_date = end_date
        self.frequency = frequency
        self.dt_column = dt_column
        self.nr_column = nr_column
        self.min_value = min_value
        self.max_value = max_value

    def get_date_range(self) -> pd.date_range:
        return pd.date_range(
            start=self.start_date, end=self.end_date, freq=self.frequency
        )

    def get_timeseries(self) -> pd.DataFrame:
        timestamp_date_range = self.get_date_range()
        timeseries_df = pd.DataFrame(timestamp_date_range, columns=[self.dt_column])
        timeseries_df[self.nr_column] = np.random.randint(
            self.min_value, self.max_value, size=len(timestamp_date_range)
        )
        return timeseries_df