apmtools 0.2.35__tar.gz → 0.2.37__tar.gz

{apmtools-0.2.35 → apmtools-0.2.37}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: apmtools
-Version: 0.2.35
+Version: 0.2.37
 Summary: A collection of tools for processing air pollution monitoring data
 Project-URL: Homepage, https://github.com/federlorenz/apmtools
 Author-email: Federico Lorenzetti <lorenzetti.federico@gmail.com>

{apmtools-0.2.35 → apmtools-0.2.37}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "apmtools"
-version = "0.2.35"
+version = "0.2.37"
 authors = [
   { name="Federico Lorenzetti", email="lorenzetti.federico@gmail.com" },
 ]

{apmtools-0.2.35 → apmtools-0.2.37}/src/apmtools/classes.py

@@ -449,7 +449,7 @@ class Dataset(DictionaryPlus):
             a.filter_key = self.filter_key
             return a
 
-    def scan_folder(self, directory="./", levels=[], level=0, monitor=None, levels_dict=None, gmt_timezone_shift=0, interpolate=False, add_m={}):
+    def scan_folder(self, directory="./", levels=[], level=0, monitor=None, levels_dict=None, utc_timezone_shift=0, interpolate=False, add_m={}):
 
         from .data_processing import upas_processing, lascar_processing, purple_processing, lcm_processing
 
@@ -523,7 +523,7 @@ class Dataset(DictionaryPlus):
                         case "lcm":
                             try:
                                 processed = lcm_processing(
-                                    directory, file=j, interpolate_data=interpolate)
+                                    directory, file=j, interpolate_data=interpolate, timezone_shift=timedelta(hours=utc_timezone_shift))
                                 for k, v in levels_dict.items():
                                     if (v not in ["None", "_", "-", None]) and (k not in ["monitor", "", None, "-", "_"]):
                                         processed.m[k] = v
@@ -538,7 +538,7 @@ class Dataset(DictionaryPlus):
                         case "purple":
                             try:
                                 processed = purple_processing(
-                                    f"{directory}/", timezone_shift=timedelta(hours=gmt_timezone_shift), interpolate_data=interpolate)
+                                    f"{directory}/", timezone_shift=timedelta(hours=utc_timezone_shift), interpolate_data=interpolate)
                                 for k, v in levels_dict.items():
                                     if (v not in ["None", "_", "-", None]) and (k not in ["monitor", "", None, "-", "_"]):
                                         processed.m[k] = v
@@ -564,7 +564,7 @@ class Dataset(DictionaryPlus):
                             if levels[r] not in levels[:level+1]:
                                 levels_dict[levels[r]] = None
                     self.scan_folder(directory=f"{directory}{j}/", levels=levels,
-                                     level=level+1, monitor=monitor, levels_dict=levels_dict, gmt_timezone_shift=gmt_timezone_shift, interpolate=interpolate, add_m=add_m)
+                                     level=level+1, monitor=monitor, levels_dict=levels_dict, utc_timezone_shift=utc_timezone_shift, interpolate=interpolate, add_m=add_m)
 
     def save_summary(self, save_csv=True, filename="./", columns={}, merged=True):
         types_in = list(set(type(v) for v in self.values()))

{apmtools-0.2.35 → apmtools-0.2.37}/src/apmtools/data_processing.py

@@ -308,6 +308,14 @@ def to_datetime(x):
         ':')[0]), int(x.split('T')[1].split(':')[1]), int(x.split('T')[1].split(':')[2][:-1])
     return dt.datetime(year, month, day, hour, minute, second)
 
+
+def to_datetime_lcm(x):
+    year, month, day = int(x.split('T')[0].split(
+        '-')[0]), int(x.split('T')[0].split('-')[1]), int(x.split('T')[0].split('-')[2])
+    hour, minute, second = int(x.split('T')[1].split(
+        ':')[0]), int(x.split('T')[1].split(':')[1]), int(x.split('T')[1].split(':')[2].split(".")[0])
+    return dt.datetime(year, month, day, hour, minute, second)
+
 def to_datetime_polar(x):
     year, month, day = int(x.split('T')[0].split(
         '-')[0]), int(x.split('T')[0].split('-')[1]), int(x.split('T')[0].split('-')[2])
@@ -842,15 +850,16 @@ def lascar_processing(directory, file, interpolation=1,interval="30 seconds", in
     return out
 
 
-def lcm_processing(directory, file, interpolation=1, interval="300 seconds", interpolate_data=True):
+def lcm_processing(directory, file, interpolation=1, interval="300 seconds", interpolate_data=True, timezone_shift=dt.timedelta(hours=0)):
     numeric = ["PM2.5",	"PM10",	"CO2",	"NO2",	"Temperature",	"Humidity"]
-    dtformat = '%Y-%m-%dT%H:%M:%S'
-    df = pd.read_csv(directory+file,  index_col="timestamp",
-                     date_format={'Time': dtformat})
+    df = pd.read_csv(directory+file)
+    df['timestamp'] = df['timestamp'].map(to_datetime_lcm)
+    df.set_index('timestamp', inplace=True)
     if interpolate_data:
         df = interpolate(df, 300, interpolation, pd.Timedelta(
             '00:06:00'), numeric_columns=numeric, add_binary_counter=False)
         df = keep_interval(df, interval)
+    df.index = df.index + timezone_shift
     out = Lcm(df)
     return out