Clean taxis data further and add source to readme

duzelin1 · Oct 9, 2021 · 483305e · 483305e
1 parent 4a44311
commit 483305e
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 20 deletions.
diff --git a/README.md b/README.md
@@ -21,3 +21,5 @@ A partial list of where these datasets originate from.
 - `penguins`: https://github.com/allisonhorst/penguins
 
 - `planets`: https://exoplanets.nasa.gov/exoplanet-catalog/
+
+- `taxis`: https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page
diff --git a/process/taxis.py b/process/taxis.py
@@ -36,6 +36,7 @@
         .assign(pickup_borough=raw["pulocationid"].map(loc["borough"]))
         .assign(dropoff_borough=raw["dolocationid"].map(loc["borough"]))
         .loc[lambda x: x.eval("dropoff - pickup").dt.seconds < MAX_TRIP_DURATION]
+        .loc[lambda x: x["fare"] > 0]
     )
 
     clean.to_csv("taxis.csv", index=False)
Original file line number	Diff line number	Diff line change
Expand Up		@@ -21,3 +21,5 @@ A partial list of where these datasets originate from.
		- `penguins`: https://github.com/allisonhorst/penguins

		- `planets`: https://exoplanets.nasa.gov/exoplanet-catalog/

		- `taxis`: https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page