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 #1597 from Azure/release_update/Release-112

Browse Source 
update samples from Release-112 as a part of  SDK release
This commit is contained in:
Harneet Virk
2021-09-24 14:44:53 -07:00
committed by GitHub
parent 4cac072fa4 c56c2c3525
commit a66a92e338
1 changed files with 10 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
how-to-use-azureml/machine-learning-pipelines/nyc-taxi-data-regression-model-building/scripts/prepdata/normalize.py
View File

@@ -28,13 +28,21 @@ replaced_distance_vals_df = (replaced_stfor_vals_df.replace({"distance": ".00"},
normalized_df = replaced_distance_vals_df.astype({"distance": 'float64'}) normalized_df = replaced_distance_vals_df.astype({"distance": 'float64'})
def time_to_us(time_str):
hh, mm , ss = map(int, time_str.split(':'))
return (ss + 60 * (mm + 60 * hh)) * (10**6)
temp = pd.DatetimeIndex(normalized_df["pickup_datetime"]) temp = pd.DatetimeIndex(normalized_df["pickup_datetime"])
normalized_df["pickup_date"] = temp.date normalized_df["pickup_date"] = pd.to_datetime(temp.date)
normalized_df["pickup_time"] = temp.time normalized_df["pickup_time"] = temp.time
normalized_df["pickup_time"] = normalized_df["pickup_time"].apply(lambda x: time_to_us(str(x)))
temp = pd.DatetimeIndex(normalized_df["dropoff_datetime"]) temp = pd.DatetimeIndex(normalized_df["dropoff_datetime"])
normalized_df["dropoff_date"] = temp.date normalized_df["dropoff_date"] = pd.to_datetime(temp.date)
normalized_df["dropoff_time"] = temp.time normalized_df["dropoff_time"] = temp.time
normalized_df["dropoff_time"] = normalized_df["dropoff_time"].apply(lambda x: time_to_us(str(x)))
del normalized_df["pickup_datetime"] del normalized_df["pickup_datetime"]
del normalized_df["dropoff_datetime"] del normalized_df["dropoff_datetime"]