[BSE-4271] Add NYC Taxi benchmark code (#6)

benchmarks/nyc_taxi_preciptation.py

@@ -0,0 +1,97 @@
+"""
+NYC Taxi Monthly Trips with Precipitation
+
+Similar to:
+https://github.com/toddwschneider/nyc-taxi-data/blob/c65ad8332a44f49770644b11576c0529b40bbc76/citibike_comparison/analysis/analysis_queries.sql#L1
+"""
+
+import time
+
+import pandas as pd
+
+import bodo
+
+
+@bodo.jit(cache=True)
+def get_monthly_travels_weather():
+    start = time.time()
+    central_park_weather_observations = pd.read_csv(
+        "s3://bodo-example-data/nyc-taxi/central_park_weather.csv", parse_dates=["DATE"]
+    )
+    central_park_weather_observations = central_park_weather_observations.rename(
+        columns={"DATE": "date", "PRCP": "precipitation"}, copy=False
+    )
+    fhvhv_tripdata = pd.read_parquet("s3://bodo-example-data/nyc-taxi/fhvhv_tripdata/")
+    end = time.time()
+    print("Reading Time: ", (end - start))
+
+    start = time.time()
+
+    central_park_weather_observations["date"] = central_park_weather_observations[
+        "date"
+    ].dt.date
+    fhvhv_tripdata["date"] = fhvhv_tripdata["pickup_datetime"].dt.date
+    fhvhv_tripdata["month"] = fhvhv_tripdata["pickup_datetime"].dt.month
+    fhvhv_tripdata["hour"] = fhvhv_tripdata["pickup_datetime"].dt.hour
+    fhvhv_tripdata["weekday"] = fhvhv_tripdata["pickup_datetime"].dt.dayofweek.isin(
+        [1, 2, 3, 4, 5]
+    )
+
+    monthly_trips_weather = fhvhv_tripdata.merge(
+        central_park_weather_observations, on="date", how="inner"
+    )
+    monthly_trips_weather["date_with_precipitation"] = (
+        monthly_trips_weather["precipitation"] > 0.1
+    )
+
+    def get_time_bucket(t):
+        bucket = "other"
+        if t in (8, 9, 10):
+            bucket = "morning"
+        elif t in (11, 12, 13, 14, 15):
+            bucket = "midday"
+        elif t in (16, 17, 18):
+            bucket = "afternoon"
+        elif t in (19, 20, 21):
+            bucket = "evening"
+        return bucket
+
+    monthly_trips_weather["time_bucket"] = monthly_trips_weather.hour.map(
+        get_time_bucket
+    )
+    monthly_trips_weather = monthly_trips_weather.groupby(
+        [
+            "PULocationID",
+            "DOLocationID",
+            "month",
+            "weekday",
+            "date_with_precipitation",
+            "time_bucket",
+        ],
+        as_index=False,
+    ).agg({"hvfhs_license_num": "count", "trip_miles": "mean"})
+    monthly_trips_weather = monthly_trips_weather.sort_values(
+        by=[
+            "PULocationID",
+            "DOLocationID",
+            "month",
+            "weekday",
+            "date_with_precipitation",
+            "time_bucket",
+        ]
+    )
+    monthly_trips_weather = monthly_trips_weather.rename(
+        columns={
+            "hvfhs_license_num": "trips",
+            "trip_miles": "avg_distance",
+        },
+        copy=False,
+    )
+    end = time.time()
+    print("Monthly Taxi Travel Times Computation Time: ", end - start)
+    print(monthly_trips_weather.head())
+    return monthly_trips_weather
+
+
+if __name__ == "__main__":
+    get_monthly_travels_weather()

examples/05-Business-Usecases-at-Scale/4-Transportation-and-Logistics.ipynb

@@ -193,7 +193,10 @@
     "    start = time.time()\n",
     "    central_park_weather_observations = pd.read_csv(\n",
     "        \"s3://bodo-example-data/nyc-taxi/central_park_weather.csv\", \n",
-    "        parse_dates=[\"date\"]\n",
+    "        parse_dates=[\"DATE\"]\n",
+    "    )\n",
+    "    central_park_weather_observations = central_park_weather_observations.rename(\n",
+    "        columns={\"DATE\": \"date\", \"PRCP\": \"precipitation\"}, copy=False\n",
     "    )\n",
     "    central_park_weather_observations[\"date\"] = central_park_weather_observations[\n",
     "        \"date\"\n",
@@ -634,4 +637,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}

examples/05-Business-Usecases-at-Scale/8-Terminal-examples/3-Transportation-and-Logistics/3-monthly_taxi_travel_times.py

@@ -23,12 +23,14 @@
 def get_monthly_travels_weather():
     start = time.time()
     central_park_weather_observations = pd.read_csv(
-        "s3://bodo-example-data/nyc-taxi/central_park_weather.csv", parse_dates=["date"]
+        "s3://bodo-example-data/nyc-taxi/central_park_weather.csv", parse_dates=["DATE"]
+    )
+    central_park_weather_observations = central_park_weather_observations.rename(
+        columns={"DATE": "date", "PRCP": "precipitation"}, copy=False
     )
     central_park_weather_observations["date"] = central_park_weather_observations[
         "date"
     ].dt.date
-
     green_taxi = pd.read_csv(
         "s3://bodo-example-data/nyc-taxi/green_tripdata_2019.csv",
         usecols=[0, 1, 5, 6, 8],