CGMPlot (cgm_df:pandas.core.frame.DataFrame, diet_df:Optional[pandas.core.frame.DataFrame]=None, cgm_date_col:str='collection_timestamp', gluc_col:str='glucose', diet_date_col:str='collection_timestamp', diet_text_col:str='shortname_eng', ax:Optional[matplotlib.axes._axes.Axes]=None, smooth:bool=False, sleep_tuples:Optional[List[Tuple[pandas._libs.tslibs.timestamps. Timestamp,pandas._libs.tslibs.timestamps.Timestamp]]]=None)
Initialize a CGMPlot object.
Args: cgm_df (pd.DataFrame): DataFrame containing the glucose measurements. diet_df (Optional[pd.DataFrame], optional): DataFrame containing the diet data. Defaults to None. cgm_date_col (str, optional): Name of the date column in cgm_df. Defaults to “Date”. gluc_col (str, optional): Name of the glucose column in cgm_df. Defaults to “glucose”. diet_date_col (str, optional): Name of the date column in diet_df. Defaults to “Date”. diet_text_col (str, optional): Name of the text column in diet_df. Defaults to “shortname_eng”. ax (Optional[plt.Axes], optional): Matplotlib Axes object to plot on. Defaults to None. smooth (bool, optional): Apply smoothing to the glucose curve. Defaults to False. sleep_tuples (Optional[List[Tuple[pd.Timestamp, pd.Timestamp]]], optional): List of sleep start and end times. Defaults to None.
cgm_df= pd.read_parquet("./examples/cgm/cgm.parquet")
cgm_df.head()| glucose | |||
|---|---|---|---|
| participant_id | collection_timestamp | connection_id | |
| 0 | 2020-05-25 10:48:00+03:00 | 1000001 | 111.6 |
| 2020-05-25 11:03:00+03:00 | 1000001 | 79.2 | |
| 2020-05-25 11:18:00+03:00 | 1000001 | 84.6 | |
| 2020-05-25 11:33:00+03:00 | 1000001 | 106.2 | |
| 2020-05-25 11:48:00+03:00 | 1000001 | 102.6 |
diet_df = pd.read_parquet("./examples/diet_logging/diet.parquet")
diet_df.head()| collection_timestamp | food_id | weight | shortname_eng | ||
|---|---|---|---|---|---|
| participant_id | cohort | ||||
| 0 | 10k | 2020-05-25 08:15:00+03:00 | 1007294 | 40.0 | Coffee |
| 10k | 2020-05-25 08:15:00+03:00 | 1007417 | 87.0 | Yellow Cheese | |
| 10k | 2020-05-25 08:15:00+03:00 | 1008624 | 6.0 | Almonds | |
| 10k | 2020-05-25 08:15:00+03:00 | 1011642 | 12.0 | Brazil nuts | |
| 10k | 2020-05-25 10:05:00+03:00 | 1007118 | 100.0 | Hummus |
start_date = pd.to_datetime('2020-05-25', utc=True).tz_convert('Asia/Jerusalem')
end_date = pd.to_datetime('2020-05-27',utc=True).tz_convert('Asia/Jerusalem')
sample_days = cgm_df[(cgm_df.index.get_level_values('collection_timestamp') >= start_date) \
& (cgm_df.index.get_level_values('collection_timestamp') <= end_date)]cgmplt = CGMPlot(cgm_df=sample_days.reset_index(),
cgm_date_col="collection_timestamp",
gluc_col="glucose",
diet_df=diet_df.iloc[9:],
diet_date_col="collection_timestamp",
smooth=True)
cgmplt.plot()
AGP (cgm_df:pandas.core.frame.DataFrame, cgm_date_col:str='collection_timestamp', gluc_col:str='glucose', ax:Optional[matplotlib.axes._axes.Axes]=None)
Initialize an AGP object.
Args: cgm_df (pd.DataFrame): DataFrame containing the glucose measurements. cgm_date_col (str, optional): Name of the date column in cgm_df. Defaults to “collection_timestamp”. gluc_col (str, optional): Name of the glucose column in cgm_df. Defaults to “glucose”. ax (Optional[plt.Axes], optional): Matplotlib Axes object to plot on. Defaults to None.
agp = AGP(cgm_df=cgm_df.reset_index(), cgm_date_col="collection_timestamp", gluc_col="glucose")
agp.plot()