Update rapids and add regex=True.

Reformat debug_heatmap.

exploration/debug_heatmap.py

@@ -14,15 +14,9 @@
 # ---
 
 # %%
-import os, sys
-import importlib
 import pandas as pd
-import numpy as np
 
-# import plotly.graph_objects as go
-from importlib import util
-from pathlib import Path
-import yaml
+from rapids.src.features.utils.utils import chunk_episodes
 
 # %%
 phone_data_yield = pd.read_csv(
@@ -36,23 +30,29 @@ time_segments_labels = pd.read_csv(
 # %%
 phone_data_yield["assigned_segments"] = phone_data_yield[
     "assigned_segments"
-].str.replace(r"_RR\d+SS#", "#")
+].str.replace(r"_RR\d+SS#", "#", regex=True)
 time_segments_labels["label"] = time_segments_labels["label"].str.replace(
-    r"_RR\d+SS$", ""
+    r"_RR\d+SS$", "", regex=True
 )
 
 
 # %% tags=[]
-def filter_data_by_segment(data, time_segment):
+def filter_data_by_segment(data, time_segment_current):
     data.dropna(subset=["assigned_segments"], inplace=True)
     if data.shape[0] == 0:  # data is empty
         data["local_segment"] = data["timestamps_segment"] = None
         return data
 
-    datetime_regex = "[0-9]{4}[\-|\/][0-9]{2}[\-|\/][0-9]{2} [0-9]{2}:[0-9]{2}:[0-9]{2}"
-    timestamps_regex = "[0-9]{13}"
-    segment_regex = "\[({}#{},{};{},{})\]".format(
-        time_segment, datetime_regex, datetime_regex, timestamps_regex, timestamps_regex
+    datetime_regex = (
+        r"[0-9]{4}[\-|\/][0-9]{2}[\-|\/][0-9]{2} [0-9]{2}:[0-9]{2}:[0-9]{2}"
+    )
+    timestamps_regex = r"[0-9]{13}"
+    segment_regex = r"\[({}#{},{};{},{})\]".format(
+        time_segment_current,
+        datetime_regex,
+        datetime_regex,
+        timestamps_regex,
+        timestamps_regex,
     )
     data["local_segment"] = data["assigned_segments"].str.extract(
         segment_regex, expand=True
@@ -147,15 +147,18 @@ def getDataForPlot(phone_data_yield_per_segment):
         .fillna(0)
     )
 
-    # transpose the dataframe per local start datetime of the segment and discard the useless index layer
+    # transpose the dataframe per local start datetime of the segment
+    # and discard the useless index layer
     phone_data_yield_per_segment = phone_data_yield_per_segment.groupby(
         "local_segment_start_datetimes"
     )[["minutes_after_segment_start", "sensor"]].apply(
         lambda x: x.set_index("minutes_after_segment_start").transpose()
     )
-    phone_data_yield_per_segment.index = phone_data_yield_per_segment.index.get_level_values(
+    phone_data_yield_per_segment.index = (
+        phone_data_yield_per_segment.index.get_level_values(
             "local_segment_start_datetimes"
         )
+    )
     return phone_data_yield_per_segment
 
 
@@ -227,9 +230,13 @@ phone_data_yield_per_segment.tail()
 # # A workaround
 
 # %%
-phone_data_yield_per_segment["local_segment_start_datetimes", "minutes_after_segment_start"] = phone_data_yield_per_segment[
+phone_data_yield_per_segment[
+    "local_segment_start_datetimes", "minutes_after_segment_start"
+] = phone_data_yield_per_segment[
     ["local_segment_start_datetimes", "minutes_after_segment_start"]
-].drop_duplicates(keep="first")
+].drop_duplicates(
+    keep="first"
+)
 
 # %%
 phone_data_yield_per_segment.set_index(
@@ -244,8 +251,9 @@ phone_data_yield_per_segment.head()
 # %% [markdown]
 # # Retry
 
+
 # %%
-def getDataForPlot(phone_data_yield_per_segment):
+def get_data_for_plot(phone_data_yield_per_segment):
     # calculate the length (in minute) of per segment instance
     phone_data_yield_per_segment["length"] = (
         phone_data_yield_per_segment["timestamps_segment"]
@@ -292,7 +300,10 @@ def getDataForPlot(phone_data_yield_per_segment):
         full_index,
         names=("local_segment_start_datetimes", "minutes_after_segment_start"),
     )
-    phone_data_yield_per_segment = phone_data_yield_per_segment.drop_duplicates(subset=["local_segment_start_datetimes", "minutes_after_segment_start"],keep="first")
+    phone_data_yield_per_segment = phone_data_yield_per_segment.drop_duplicates(
+        subset=["local_segment_start_datetimes", "minutes_after_segment_start"],
+        keep="first",
+    )
     phone_data_yield_per_segment = (
         phone_data_yield_per_segment.set_index(
             ["local_segment_start_datetimes", "minutes_after_segment_start"]
@@ -302,15 +313,18 @@ def getDataForPlot(phone_data_yield_per_segment):
         .fillna(0)
     )
 
-    # transpose the dataframe per local start datetime of the segment and discard the useless index layer
+    # transpose the dataframe per local start datetime of the segment
+    # and discard the useless index layer
     phone_data_yield_per_segment = phone_data_yield_per_segment.groupby(
         "local_segment_start_datetimes"
     )[["minutes_after_segment_start", "sensor"]].apply(
         lambda x: x.set_index("minutes_after_segment_start").transpose()
     )
-    phone_data_yield_per_segment.index = phone_data_yield_per_segment.index.get_level_values(
+    phone_data_yield_per_segment.index = (
+        phone_data_yield_per_segment.index.get_level_values(
             "local_segment_start_datetimes"
         )
+    )
     return phone_data_yield_per_segment
 
 
@@ -318,6 +332,6 @@ def getDataForPlot(phone_data_yield_per_segment):
 phone_data_yield_per_segment = filter_data_by_segment(phone_data_yield, time_segment)
 
 # %%
-data_for_plot_per_segment = getDataForPlot(phone_data_yield_per_segment)
+data_for_plot_per_segment = get_data_for_plot(phone_data_yield_per_segment)
 
 # %%

rapids

@@ -1 +1 @@
-Subproject commit 63f5a526fce4d288499168e1701adadb8b885d82
+Subproject commit 059774bda10545a83ab282f59eb7a329fef9ee4c