From 7e8e922d71429ee9792cc2db1cdb6feb54c42317 Mon Sep 17 00:00:00 2001
From: junos <junos.lukan@ijs.si>
Date: Wed, 15 Dec 2021 18:25:53 +0100
Subject: [PATCH] Debugging of RAPIDS.

---
 .idea/misc.xml               | 13 ++++++
 exploration/debug_heatmap.py | 82 +++++++++++++++++++++++++++++++++++-
 rapids                       |  2 +-
 3 files changed, 95 insertions(+), 2 deletions(-)

diff --git a/.idea/misc.xml b/.idea/misc.xml
index 8962e54..b6b261d 100644
--- a/.idea/misc.xml
+++ b/.idea/misc.xml
@@ -4,4 +4,17 @@
   <component name="PyCharmProfessionalAdvertiser">
     <option name="shown" value="true" />
   </component>
+  <component name="RMarkdownSettings">
+    <option name="renderProfiles">
+      <map>
+        <entry key="file://$PROJECT_DIR$/rapids/src/visualization/merge_heatmap_sensors_per_minute_per_time_segment.Rmd">
+          <value>
+            <RMarkdownRenderProfile>
+              <option name="outputDirectoryUrl" value="file://$PROJECT_DIR$/rapids/src/visualization" />
+            </RMarkdownRenderProfile>
+          </value>
+        </entry>
+      </map>
+    </option>
+  </component>
 </project>
\ No newline at end of file
diff --git a/exploration/debug_heatmap.py b/exploration/debug_heatmap.py
index e7df82f..1e5663b 100644
--- a/exploration/debug_heatmap.py
+++ b/exploration/debug_heatmap.py
@@ -227,7 +227,7 @@ phone_data_yield_per_segment.tail()
 # # A workaround
 
 # %%
-phone_data_yield_per_segment = 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")
 
@@ -240,4 +240,84 @@ phone_data_yield_per_segment.set_index(
 # %%
 phone_data_yield_per_segment.head()
 
+
+# %% [markdown]
+# # Retry
+
+# %%
+def getDataForPlot(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"]
+        .str.split(",")
+        .apply(lambda x: int((int(x[1]) - int(x[0])) / (1000 * 60)))
+    )
+    # calculate the number of sensors logged at least one row of data per minute.
+    phone_data_yield_per_segment = (
+        phone_data_yield_per_segment.groupby(
+            ["local_segment", "length", "local_date", "local_hour", "local_minute"]
+        )[["sensor", "local_date_time"]]
+        .max()
+        .reset_index()
+    )
+    # extract local start datetime of the segment from "local_segment" column
+    phone_data_yield_per_segment["local_segment_start_datetimes"] = pd.to_datetime(
+        phone_data_yield_per_segment["local_segment"].apply(
+            lambda x: x.split("#")[1].split(",")[0]
+        )
+    )
+    # calculate the number of minutes after local start datetime of the segment
+    phone_data_yield_per_segment["minutes_after_segment_start"] = (
+        (
+            phone_data_yield_per_segment["local_date_time"]
+            - phone_data_yield_per_segment["local_segment_start_datetimes"]
+        )
+        / pd.Timedelta(minutes=1)
+    ).astype("int")
+
+    # impute missing rows with 0
+    columns_for_full_index = phone_data_yield_per_segment[
+        ["local_segment_start_datetimes", "length"]
+    ].drop_duplicates(keep="first")
+    columns_for_full_index = columns_for_full_index.apply(
+        lambda row: [
+            [row["local_segment_start_datetimes"], x] for x in range(row["length"] + 1)
+        ],
+        axis=1,
+    )
+    full_index = []
+    for columns in columns_for_full_index:
+        full_index = full_index + columns
+    full_index = pd.MultiIndex.from_tuples(
+        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.set_index(
+            ["local_segment_start_datetimes", "minutes_after_segment_start"]
+        )
+        .reindex(full_index)
+        .reset_index()
+        .fillna(0)
+    )
+
+    # 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(
+        "local_segment_start_datetimes"
+    )
+    return 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)
+
 # %%
diff --git a/rapids b/rapids
index d2ed73d..e5cc025 160000
--- a/rapids
+++ b/rapids
@@ -1 +1 @@
-Subproject commit d2ed73dccfac65ce503c1b510182fe5ef1516508
+Subproject commit e5cc02501f629c96641dfd1bcd1f7fcfd0d55462