avoca 0.11.2__tar.gz → 0.11.3__tar.gz

{avoca-0.11.2 → avoca-0.11.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: avoca
-Version: 0.11.2
+Version: 0.11.3
 Summary: @voc@: Quality assessement of measurement data
 Project-URL: Homepage, https://gitlab.com/empa503/atmospheric-measurements/avoca
 Project-URL: Bug Tracker, https://gitlab.com/empa503/atmospheric-measurements/avoca/-/issues

{avoca-0.11.2 → avoca-0.11.3}/avoca/bindings/gcwerks.py

@@ -93,8 +93,9 @@ flag_values = {
 }
 
 # Show the flags and the columns they are applied to
-flags_known = list(flag_values.keys())
+flags_allowed = list(flag_values.keys())
 # Add the last values allowed in the columns
+flags_known = flags_allowed.copy()
 flags_known.extend(
     [
         "n",  # From nan
@@ -122,6 +123,7 @@ allowed_vars = [
     "C",
     "ht",
     "w",
+    "RL.report",
     "norm_ht",
     "norm_a",
     "C_ht",
@@ -221,6 +223,10 @@ def read_gcwerks(
         # Last character is the flag
         flags: pd.Series = serie_str.str[-1]
         if col[1] in cols_float:
+            # Remove the flag value when given
+            serie_str = serie_str.apply(
+                lambda x: x[:-1] if x[-1] in flags_allowed else x
+            )
             # Convert the serie to numeric
             df[col] = pd.to_numeric(serie_str, errors="coerce")
 

avoca-0.11.3/examples/get_tanks.ipynb

@@ -0,0 +1,168 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cbff1d1a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload 2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5564964a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd \n",
+    "\n",
+    "from avoca.bindings.gcwerks import read_gcwerks, export\n",
+    "\n",
+    "from pathlib import Path\n",
+    "from datetime import datetime\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bba5e278",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "\n",
+    "workdir = Path('./KSJ_flask')\n",
+    "workdir.mkdir(exist_ok=True)\n",
+    "temp_file = workdir / 'sevoflurane.dat'\n",
+    "export(\n",
+    "    workdir=workdir,\n",
+    "    gcdir=\"/agage/empa-medusa\", \n",
+    "    compounds=['sevoflurane'], \n",
+    "    out_file=temp_file, \n",
+    "    date_start=datetime(2010, 1, 1),\n",
+    "    variables=['C', 'RL.report' ]\n",
+    "    \n",
+    ")\n",
+    "df_gcwerks = read_gcwerks(temp_file, runtypes=['tank'])\n",
+    "df_gcwerks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dcffbe3e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mini_archive_file = \"/agage/empa-medusa/logs/hardware.log/MiniArchive2013\"\n",
+    "lines = []\n",
+    "\n",
+    "columns = [\n",
+    "    'measurement_time',\n",
+    "    'sample_id',\n",
+    "    'tank_id',\n",
+    "    'tank_material',\n",
+    "    'pressure',\n",
+    "    'lon',\n",
+    "    'lat',\n",
+    "    'sampling_time',\n",
+    "    'station', \n",
+    "    'filling_method', \n",
+    "    'sampling_volume',\n",
+    "    'operator',\n",
+    "]\n",
+    "with open(mini_archive_file, 'r') as f:\n",
+    "    for i, line in enumerate(f):\n",
+    "        if line.startswith('#'):\n",
+    "            continue\n",
+    "        if line.strip() == '':\n",
+    "            continue\n",
+    "        values = line.strip().split()\n",
+    "        if len(values) < len(columns):\n",
+    "            print(f\"Skipping line {line} with insufficient values: {line.strip()}\")\n",
+    "            continue\n",
+    "        lines.append(values[:len(columns)])\n",
+    "\n",
+    "lines\n",
+    "df = pd.DataFrame(lines, columns=columns)\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1abc794d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['tank_material'].unique()\n",
+    "df['sampling_time'] = pd.to_datetime(df['sampling_time'], format='%Y%m%d')\n",
+    "df['measurement_time'] = pd.to_datetime(df['measurement_time'], format='%y%m%d.%H%M')\n",
+    "df_ksg = df.loc[df['station'] == 'KSG']\n",
+    "df_ksg"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8664c16a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_gcwerks_ksg = df_gcwerks.loc[df_gcwerks[('-', 'sample')].str.startswith('KSG')].copy()\n",
+    "\n",
+    "# access the string from 3:9 of the column \n",
+    "df_gcwerks_ksg['sampling_time'] = pd.to_datetime(df_gcwerks_ksg[('-', 'sample')].str[3:9], format='%y%m%d')\n",
+    "df_gcwerks_ksg"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dbc981ad",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_gcwerks_ksg"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b5a49cd0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.figure(figsize=(10, 6))\n",
+    "df_gcwerks_ksg.plot(x='sampling_time', y=('sevoflurane', 'C'), kind='scatter', title='KSG Sevoflurane Concentration')\n",
+    "plt.savefig(workdir / 'KSG_sevoflurane_concentration.png')\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

{avoca-0.11.2 → avoca-0.11.3}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "avoca"
-version = "0.11.2"
+version = "0.11.3"
 authors = [
   { name="Lionel Constantin", email="lionel.constantin@empa.ch" },
 ]