jprdonnelly/MachineLearningNotebooks
1
0
Fork 0
mirror of https://github.com/Azure/MachineLearningNotebooks.git synced 2025-12-19 17:17:04 -05:00
Code Issues Projects Releases Wiki Activity

Merge pull request #459 from datashinobi/yassine/datadrift2

Browse Source 
fix link to config nb & settingwithcopywarning
This commit is contained in:
Roope Astala
2019-07-03 12:41:31 -04:00
committed by GitHub
parent 14ecfb0bf3 e97e4742ba
commit 9e0fc4f0e7
1 changed files with 707 additions and 707 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
how-to-use-azureml/data-drift/azure-ml-datadrift.ipynb
View File

@@ -82,7 +82,7 @@
"source": [
"## Set up Configuraton and Create Azure ML Workspace\n",
"\n",
"If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [configuration notebook](../../../configuration.ipynb) first if you haven't already to establish your connection to the AzureML Workspace."
"If you are using an Azure Machine Learning Notebook VM, you are all set. Otherwise, go through the [configuration notebook](../../configuration.ipynb) first if you haven't already to establish your connection to the AzureML Workspace."
]
},
{
@@ -140,26 +140,26 @@
"\n",
"columns = ['usaf', 'wban', 'datetime', 'latitude', 'longitude', 'elevation', 'windAngle', 'windSpeed', 'temperature', 'stationName', 'p_k']\n",
"\n",
"\n",
"def enrich_weather_noaa_data(noaa_df):\n",
" hours_in_day = 23\n",
" week_in_year = 52\n",
" \n",
" noaa_df[\"hour\"] = noaa_df[\"datetime\"].dt.hour\n",
" noaa_df[\"weekofyear\"] = noaa_df[\"datetime\"].dt.week\n",
"\n",
" noaa_df[\"sine_weekofyear\"] = noaa_df['datetime'].transform(lambda x: np.sin((2*np.pi*x.dt.week-1)/week_in_year))\n",
" noaa_df[\"cosine_weekofyear\"] = noaa_df['datetime'].transform(lambda x: np.cos((2*np.pi*x.dt.week-1)/week_in_year))\n",
"\n",
" noaa_df[\"sine_hourofday\"] = noaa_df['datetime'].transform(lambda x: np.sin(2*np.pi*x.dt.hour/hours_in_day))\n",
" noaa_df[\"cosine_hourofday\"] = noaa_df['datetime'].transform(lambda x: np.cos(2*np.pi*x.dt.hour/hours_in_day))\n",
" noaa_df = noaa_df.assign(hour=noaa_df[\"datetime\"].dt.hour,\n",
" weekofyear=noaa_df[\"datetime\"].dt.week,\n",
" sine_weekofyear=noaa_df['datetime'].transform(lambda x: np.sin((2*np.pi*x.dt.week-1)/week_in_year)),\n",
" cosine_weekofyear=noaa_df['datetime'].transform(lambda x: np.cos((2*np.pi*x.dt.week-1)/week_in_year)),\n",
" sine_hourofday=noaa_df['datetime'].transform(lambda x: np.sin(2*np.pi*x.dt.hour/hours_in_day)),\n",
" cosine_hourofday=noaa_df['datetime'].transform(lambda x: np.cos(2*np.pi*x.dt.hour/hours_in_day))\n",
" )\n",
" \n",
" return noaa_df\n",
"\n",
"\n",
"def add_window_col(input_df):\n",
" shift_interval = pd.Timedelta('-7 days') # your X days interval\n",
" df_shifted = input_df.copy()\n",
" df_shifted['datetime'] = df_shifted['datetime'] - shift_interval\n",
" df_shifted.loc[:,'datetime'] = df_shifted['datetime'] - shift_interval\n",
" df_shifted.drop(list(input_df.columns.difference(['datetime', 'usaf', 'wban', 'sine_hourofday', 'temperature'])), axis=1, inplace=True)\n",
"\n",
" # merge, keeping only observations where -1 lag is present\n",