From ea2a73e03930d2c070402a592fc24436403b0ba2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Erik=20Bj=C3=A4reholt?= <erik@bjareho.lt>
Date: Wed, 8 Nov 2023 12:39:54 +0100
Subject: [PATCH] fix: fixed pandas typing

---
 src/quantifiedme/load/eeg.py             |  6 +++---
 src/quantifiedme/load/google_activity.py | 12 ++++++------
 src/quantifiedme/load/location.py        | 11 ++++++-----
 3 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/src/quantifiedme/load/eeg.py b/src/quantifiedme/load/eeg.py
index e8fc65d..4f16a71 100644
--- a/src/quantifiedme/load/eeg.py
+++ b/src/quantifiedme/load/eeg.py
@@ -6,8 +6,8 @@
 We will also load signal quality data, to help us filter out bad data.
 """
 
-from pathlib import Path
 from collections import defaultdict
+from pathlib import Path
 
 import pandas as pd
 
@@ -33,7 +33,7 @@ def load_data():
     for timestamp, files in filesets.items():
         result = load_session(files)
         # pprint(result)
-        df = df.append(result, ignore_index=True)
+        df = pd.concat([df, pd.DataFrame(result)], ignore_index=True)
     return df
 
 
@@ -58,7 +58,7 @@ def load_session(files: dict) -> dict:
     # we have to deal with the channels, such as CP3_alpha, CP3_beta, etc.
     # for now, we will just average them all together
     channels, bands = zip(*[c.split("_") for c in df_pbb.columns])
-    channels, bands = list(set(channels)), list(set(bands))
+    channels, bands = tuple(set(channels)), tuple(set(bands))
 
     df = pd.DataFrame(index=df_pbb.index)
     for band in bands:
diff --git a/src/quantifiedme/load/google_activity.py b/src/quantifiedme/load/google_activity.py
index 9ab0a65..e0df510 100644
--- a/src/quantifiedme/load/google_activity.py
+++ b/src/quantifiedme/load/google_activity.py
@@ -1,6 +1,8 @@
 import json
-import pandas as pd
+from pathlib import Path
 
+import matplotlib.pyplot as plt
+import pandas as pd
 from quantifiedme.config import load_config
 
 
@@ -11,11 +13,11 @@ def load_activity_history() -> pd.DataFrame:
     Specifically the search history, for now.
     """
     config = load_config()
-    activity_file = config["data"]["google_takeout"]["activity"]
+    activity_file = Path(config["data"]["google_takeout"]["activity"]).expanduser()
     with open(activity_file) as f:
         activity = pd.DataFrame(json.load(f))
 
-    activity["time"] = pd.to_datetime(activity["time"])
+    activity["time"] = pd.to_datetime(activity["time"], format="ISO8601")
     # set the index to the time
     activity = activity.set_index("time")
     return activity
@@ -28,8 +30,6 @@ def load_activity_history() -> pd.DataFrame:
     print(activity[:10][["title", "titleUrl"]])
     print(f"Length: {len(activity)}")
 
-    import matplotlib.pyplot as plt
-
     # plot a histogram with count of serches by hour of day
     # activity["hour"] = activity.index.hour
     # activity["hour"].hist(bins=24)
@@ -41,6 +41,6 @@ def load_activity_history() -> pd.DataFrame:
     # plt.show()
 
     # now plot by year-month
-    activity["year-month"] = activity.index.strftime("%Y-%m")
+    activity["year-month"] = activity.index.map(lambda dt: dt.strftime("%Y-%m"))
     activity["year-month"].hist(bins=12 * 11)
     plt.show()
diff --git a/src/quantifiedme/load/location.py b/src/quantifiedme/load/location.py
index 8e7f012..1b7f28e 100644
--- a/src/quantifiedme/load/location.py
+++ b/src/quantifiedme/load/location.py
@@ -4,6 +4,7 @@
 from pathlib import Path
 
 import click
+import numpy as np
 import pandas as pd
 from matplotlib import pyplot as plt
 from tqdm import tqdm
@@ -126,12 +127,12 @@ def _proximity_to_location(
     lat, lon = loc
     dist = ((df["lat"] - lat) ** 2 + (df["long"] - lon) ** 2) ** 0.5
     dist = dist[dist < threshold_radius]
-    dist = pd.DataFrame(dist, columns=["dist"])
-    dist["duration"] = 10 / 60
-    dist = dist.resample("24H").apply({"duration": "sum"})
+    df_dist = pd.DataFrame(dist, columns=["dist"])
+    df_dist["duration"] = 10 / 60
+    df_dist = df_dist.resample("24H").apply({"duration": np.sum})  # type: ignore
     if verbose:
-        print(dist)
-    return dist["duration"]
+        print(df_dist)
+    return df_dist["duration"]
 
 
 def plot_df_duration(df, title, save: str | None = None) -> None: