Progress toward getting the evaluation integrated

This will compare the MEG and ECG directly

src/hrvmeg/evaluate.py

@@ -3,10 +3,11 @@ import mpld3
 import numpy as np
 import pandas as pd
 import scipy.signal as signal
+from data import GetRPeaks
 
 
 class CompareMEGICAtoECG:
-    def __init__(self, output_sub_dir, subject_id, subject_path, ICA_value):
+    def __init__(self, output_sub_dir, subject_id, subject_path):
         """
         The function takes in the subject_id, subject_path, output_sub_dir, and ICA_value and assigns
         them to the class.
@@ -20,130 +21,9 @@ class CompareMEGICAtoECG:
         self.subject_path = subject_path
         self.subject_id = subject_id
         self.output_sub_dir = output_sub_dir
-        self.ICA_value = ICA_value
 
-    def get_ICA_RR_intervals(self):
-        """
-        The function takes in a .CSV file with two columns: time and a component value. It then uses
-        scipy's peak detection function to find peaks in the component value. It then plots the peaks
-        and saves the plot as a .HTML file
-        """
-
-        #############################################################
-
-        df = pd.DataFrame()
-
-        # get time and component from .CSV file
-        arr_Time_Series = pd.read_csv(self.subject_path).iloc[:, 0].T.to_numpy()
-        component_value = pd.read_csv(self.subject_path).iloc[:, 1].T.to_numpy()
-
-        df["Time"] = arr_Time_Series
-        df[f"ICA_Values_{self.ICA_value}"] = component_value
-
-        hr_arr = df.to_numpy()
-
-        #############################################################
-
-        # Assign paths
-        stats_component = f"{self.output_sub_dir}/{self.subject_id}_HR_component.csv"
-        graph_component = f"{self.output_sub_dir}/{self.subject_id}_Plot_{self.ICA_value}.png"
-
-        #############################################################
-
-        component_time = hr_arr[:, 0]
-        ICA_component_value = hr_arr[:, 1]
-
-        # attempt to flip values if signal is inverted
-        if np.median(ICA_component_value) > 0.00:
-            ICA_component_value = -ICA_component_value
-
-        df[f"ICA_Values_{self.ICA_value}"] = ICA_component_value
-
-        #                                   SCIPY PEAK DETECTION
-
-        ###################################################################################################
-
-        distance = 150
-
-        # filter height to peaks within the top 5% of largest values
-        num_to_filter_component = round(len(ICA_component_value) * 0.045)
-        height_component = (
-            sum(sorted(ICA_component_value)[-num_to_filter_component:])
-        ) / num_to_filter_component
-
-        # Load sample ECG signal & extract R-peaks
-        component_rpeaks, _ = signal.find_peaks(
-            ICA_component_value, height=height_component, distance=distance, prominence=3.5
-        )
-
-        #                                   PYHRV PEAK DETECTION
-        ########################################################################################################
-
-        # t_component, filtered_signal, component_rpeaks = biosppy.signals.ecg.ecg(ICA_component_value, sampling_rate=500)[:3]
-
-        #                                    Plots Component Peaks
-        ################################################################################################
-
-        length_of_component_time_series = np.amax(component_time)
-
-        to_divide = 1
-
-        mini2 = 0
-        maxi2 = len(component_time) / to_divide
-
-        peaks_range = [
-            idx for idx in range(len(component_rpeaks)) if mini2 < component_rpeaks[idx] < maxi2
-        ]
-
-        peaks1 = component_rpeaks[peaks_range]
-
-        fig, ax = plt.subplots(1, 1, figsize=(12, 5))
-
-        plt.plot(component_time, ICA_component_value, linewidth=0.2)
-        plt.plot(component_time[component_rpeaks], ICA_component_value[component_rpeaks], "x")
-
-        plt.xlim([10, 480 // to_divide])
-
-        fig = plt.gcf()
-        fig.set_size_inches(12, 5)
-
-        beat_cnt = len(peaks1)
-        avg_hr = round((beat_cnt / (length_of_component_time_series)) * 60, 2)
-
-        plt.title(
-            f"{self.subject_id} RR Interval Component {self.ICA_value} \nNumber of Beats: {beat_cnt} || Average Heart Rate: {avg_hr}"
-        )
-
-        plt.savefig(graph_component, dpi=100)
-
-        # save figure as HTML file
-        html_str = mpld3.fig_to_html(fig)
-        Html_file = open(graph_component[:-4] + ".html", "w")
-        Html_file.write(html_str)
-        Html_file.close()
-
-        #                                    Writes Component RR Intervals to CSV
-        ################################################################################################################
-
-        # peak_vals = component_time[component_rpeaks]
-
-        # rr_int = []
-        # size = len(peak_vals) - 1
-
-        # for i in range(1, size):
-        #     print(peak_vals[i])
-        #     delta = peak_vals[i] - peak_vals[i - 1]
-        #     rr_int = np.append(rr_int, delta)
-
-        # df = pd.DataFrame()
-
-        # df['Time'] = peak_vals[2:]
-
-        # df = pd.DataFrame()
-
-        # df['Signal'] = ICA_component_value
-
-        # df = df.set_index('Signal')
-        # df = df.dropna()
-
-        df.to_csv(stats_component, index=False)
+    def get_ica_rr(self):
+        ica_rr = GetRPeaks(output_sub_dir = self.output_sub_dir,
+                           subject_id = self.subject_id,
+                           subject_path = self.subject_path
+                           )

src/hrvmeg/main.py

-import json
 import warnings
-from argparse import Namespace
 from pathlib import Path
 from typing import Dict
 
@@ -10,8 +8,8 @@ import typer
 
 from config import config
 from config.config import logger
-from hrvmeg import config_utils, evaluate, predict
-from py_utils import get_files, print_info
+from hrvmeg import predict
+from py_utils import config_utils, get_files, print_info
 from utils import meg_to_ica
 
 # Initialize Typer CLI app
@@ -64,7 +62,6 @@ def extract_ica_from_meg(
         #TODO add plotting here
         # fig, ax = MNE_proc.plot()
 
-        
         logger.info("✅ ICA successfully calculated on MEG data with MNE")
         with mlflow.start_run(run_name=run_name) as run:
             print_info.print_run_info(run)
@@ -87,7 +84,7 @@ def extract_ica_from_meg(
 
 @app.command()
 def label_cardiac_ic(
-    args_fp: str = "config/args.json",
+    args_fp: str = "config/args_preproc.json",
     experiment_name: str = "label_cardiac_signals",
     run_name: str = "sgd",
     test_run: bool = False,
@@ -133,7 +130,12 @@ def label_cardiac_ic(
 
 
 @app.command
-def compare_ica_and_ecg():
+def compare_ica_and_ecg(
+    args_rr: str="config/args_rr.json",
+    experiment_name: str= "compare ECG + MEG",
+    run_name: str="comparison 1"
+    test_run: bool = True
+):
     raise (NotImplementedError)