Crea un modello K-means per raggruppare il set di dati sui noleggi di biciclette a Londra

SQL

Questa query estrae i dati sulle prenotazioni di biciclette, incluse le colonne start_station_name e duration, e li unisce alle informazioni sulle stazioni. Ciò include la creazione di una colonna calcolata contenente la distanza della stazione dal centro città. Quindi, calcola gli attributi della stazione in una colonna stationstats, inclusa la durata media delle corse e il numero di corse, nonché la colonna distance_from_city_center calcolata.

Per esaminare i dati di addestramento:

1. Nella console Google Cloud, vai alla pagina BigQuery.

   Vai a BigQuery

2. Nell'editor di query, incolla la seguente query e fai clic su Esegui:

   WITH
   hs AS (
     SELECT
       h.start_station_name AS station_name,
       IF(
         EXTRACT(DAYOFWEEK FROM h.start_date) = 1
           OR EXTRACT(DAYOFWEEK FROM h.start_date) = 7,
         'weekend',
         'weekday') AS isweekday,
       h.duration,
       ST_DISTANCE(ST_GEOGPOINT(s.longitude, s.latitude), ST_GEOGPOINT(-0.1, 51.5)) / 1000
         AS distance_from_city_center
     FROM
       `bigquery-public-data.london_bicycles.cycle_hire` AS h
     JOIN
       `bigquery-public-data.london_bicycles.cycle_stations` AS s
       ON
         h.start_station_id = s.id
     WHERE
       h.start_date
       BETWEEN CAST('2015-01-01 00:00:00' AS TIMESTAMP)
       AND CAST('2016-01-01 00:00:00' AS TIMESTAMP)
   ),
   stationstats AS (
     SELECT
       station_name,
       isweekday,
       AVG(duration) AS duration,
       COUNT(duration) AS num_trips,
       MAX(distance_from_city_center) AS distance_from_city_center
     FROM
       hs
     GROUP BY
       station_name, isweekday
   )
   SELECT *
   FROM
   stationstats
   ORDER BY
   distance_from_city_center ASC;

I risultati dovrebbero essere simili ai seguenti:

BigQuery DataFrames

Prima di provare questo esempio, segui le istruzioni di configurazione di BigQuery DataFrames riportate nella guida introduttiva di BigQuery che utilizza BigQuery DataFrames. Per ulteriori informazioni, consulta la documentazione di riferimento di BigQuery DataFrames.

Per autenticarti in BigQuery, configura le Credenziali predefinite dell'applicazione. Per maggiori informazioni, vedi Configurare ADC per un ambiente di sviluppo locale.

import datetime

import pandas as pd

import bigframes
import bigframes.pandas as bpd

bigframes.options.bigquery.project = your_gcp_project_id
# Compute in the EU multi-region to query the London bicycles dataset.
bigframes.options.bigquery.location = "EU"

# Extract the information you'll need to train the k-means model in this
# tutorial. Use the read_gbq function to represent cycle hires
# data as a DataFrame.
h = bpd.read_gbq(
    "bigquery-public-data.london_bicycles.cycle_hire",
    col_order=["start_station_name", "start_station_id", "start_date", "duration"],
).rename(
    columns={
        "start_station_name": "station_name",
        "start_station_id": "station_id",
    }
)

s = bpd.read_gbq(
    # Use ST_GEOPOINT and ST_DISTANCE to analyze geographical
    # data. These functions determine spatial relationships between
    # geographical features.
    """
    SELECT
    id,
    ST_DISTANCE(
        ST_GEOGPOINT(s.longitude, s.latitude),
        ST_GEOGPOINT(-0.1, 51.5)
    ) / 1000 AS distance_from_city_center
    FROM
    `bigquery-public-data.london_bicycles.cycle_stations` s
    """
)

# Define Python datetime objects in the UTC timezone for range comparison,
# because BigQuery stores timestamp data in the UTC timezone.
sample_time = datetime.datetime(2015, 1, 1, 0, 0, 0, tzinfo=datetime.timezone.utc)
sample_time2 = datetime.datetime(2016, 1, 1, 0, 0, 0, tzinfo=datetime.timezone.utc)

h = h.loc[(h["start_date"] >= sample_time) & (h["start_date"] <= sample_time2)]

# Replace each day-of-the-week number with the corresponding "weekday" or
# "weekend" label by using the Series.map method.
h = h.assign(
    isweekday=h.start_date.dt.dayofweek.map(
        {
            0: "weekday",
            1: "weekday",
            2: "weekday",
            3: "weekday",
            4: "weekday",
            5: "weekend",
            6: "weekend",
        }
    )
)

# Supplement each trip in "h" with the station distance information from
# "s" by merging the two DataFrames by station ID.
merged_df = h.merge(
    right=s,
    how="inner",
    left_on="station_id",
    right_on="id",
)

# Engineer features to cluster the stations. For each station, find the
# average trip duration, number of trips, and distance from city center.
stationstats = merged_df.groupby(["station_name", "isweekday"]).agg(
    {"duration": ["mean", "count"], "distance_from_city_center": "max"}
)
stationstats.columns = pd.Index(
    ["duration", "num_trips", "distance_from_city_center"]
)
stationstats = stationstats.sort_values(
    by="distance_from_city_center", ascending=True
).reset_index()

# Expected output results: >>> stationstats.head(3)
# station_name	isweekday duration  num_trips	distance_from_city_center
# Borough Road...	weekday	    1110	    5749	    0.12624
# Borough Road...	weekend	    2125	    1774	    0.12624
# Webber Street...	weekday	    795	        6517	    0.164021
#   3 rows × 5 columns

SQL

Nella seguente query, l'istruzione CREATE MODEL specifica il numero di cluster da utilizzare, ovvero quattro. Nell'istruzione SELECT, la clausola EXCEPT esclude la colonna station_name perché non contiene una funzionalità. La query crea una riga univoca per station_name e solo le funzionalità sono menzionate nell'istruzione SELECT.

Per creare un modello K-means:

1. Nella console Google Cloud, vai alla pagina BigQuery.

   Vai a BigQuery

2. Nell'editor di query, incolla la seguente query e fai clic su Esegui:

   CREATE OR REPLACE MODEL `bqml_tutorial.london_station_clusters`
   OPTIONS (
     model_type = 'kmeans',
     num_clusters = 4)
   AS
   WITH
   hs AS (
     SELECT
       h.start_station_name AS station_name,
       IF(
         EXTRACT(DAYOFWEEK FROM h.start_date) = 1
           OR EXTRACT(DAYOFWEEK FROM h.start_date) = 7,
         'weekend',
         'weekday') AS isweekday,
       h.duration,
       ST_DISTANCE(ST_GEOGPOINT(s.longitude, s.latitude), ST_GEOGPOINT(-0.1, 51.5)) / 1000
         AS distance_from_city_center
     FROM
       `bigquery-public-data.london_bicycles.cycle_hire` AS h
     JOIN
       `bigquery-public-data.london_bicycles.cycle_stations` AS s
       ON
         h.start_station_id = s.id
     WHERE
       h.start_date
       BETWEEN CAST('2015-01-01 00:00:00' AS TIMESTAMP)
       AND CAST('2016-01-01 00:00:00' AS TIMESTAMP)
   ),
   stationstats AS (
     SELECT
       station_name,
       isweekday,
       AVG(duration) AS duration,
       COUNT(duration) AS num_trips,
       MAX(distance_from_city_center) AS distance_from_city_center
     FROM
       hs
     GROUP BY
       station_name, isweekday
   )
   SELECT *
   EXCEPT (station_name, isweekday)
   FROM
   stationstats;

BigQuery DataFrames

Prima di provare questo esempio, segui le istruzioni di configurazione di BigQuery DataFrames riportate nella guida introduttiva di BigQuery che utilizza BigQuery DataFrames. Per ulteriori informazioni, consulta la documentazione di riferimento di BigQuery DataFrames.

Per autenticarti in BigQuery, configura le Credenziali predefinite dell'applicazione. Per maggiori informazioni, vedi Configurare ADC per un ambiente di sviluppo locale.

from bigframes.ml.cluster import KMeans

# To determine an optimal number of clusters, construct and fit several
# K-Means objects with different values of num_clusters, find the error
# measure, and pick the point at which the error measure is at its minimum
# value.
cluster_model = KMeans(n_clusters=4)
cluster_model.fit(stationstats)
cluster_model.to_gbq(
    your_model_id,  # For example: "bqml_tutorial.london_station_clusters"
    replace=True,
)

SQL

La seguente query utilizza la funzione REGEXP_CONTAINS per trovare tutte le voci nella colonna station_name contenenti la stringa Kennington. La funzione ML.PREDICT utilizza questi valori per prevedere quali cluster potrebbero contenere queste stazioni.

Per prevedere il cluster di ogni stazione che ha la stringa Kennington nel nome:

1. Nella console Google Cloud, vai alla pagina BigQuery.

   Vai a BigQuery

2. Nell'editor di query, incolla la seguente query e fai clic su Esegui:

   WITH
   hs AS (
     SELECT
       h.start_station_name AS station_name,
       IF(
         EXTRACT(DAYOFWEEK FROM h.start_date) = 1
           OR EXTRACT(DAYOFWEEK FROM h.start_date) = 7,
         'weekend',
         'weekday') AS isweekday,
       h.duration,
       ST_DISTANCE(ST_GEOGPOINT(s.longitude, s.latitude), ST_GEOGPOINT(-0.1, 51.5)) / 1000
         AS distance_from_city_center
     FROM
       `bigquery-public-data.london_bicycles.cycle_hire` AS h
     JOIN
       `bigquery-public-data.london_bicycles.cycle_stations` AS s
       ON
         h.start_station_id = s.id
     WHERE
       h.start_date
       BETWEEN CAST('2015-01-01 00:00:00' AS TIMESTAMP)
       AND CAST('2016-01-01 00:00:00' AS TIMESTAMP)
   ),
   stationstats AS (
     SELECT
       station_name,
       isweekday,
       AVG(duration) AS duration,
       COUNT(duration) AS num_trips,
       MAX(distance_from_city_center) AS distance_from_city_center
     FROM
       hs
     GROUP BY
       station_name, isweekday
   )
   SELECT *
   EXCEPT (nearest_centroids_distance)
   FROM
   ML.PREDICT(
     MODEL `bqml_tutorial.london_station_clusters`,
     (
       SELECT *
       FROM
         stationstats
       WHERE
         REGEXP_CONTAINS(station_name, 'Kennington')
     ));

I risultati dovrebbero essere simili al seguente.

BigQuery DataFrames

Prima di provare questo esempio, segui le istruzioni di configurazione di BigQuery DataFrames riportate nella guida introduttiva di BigQuery che utilizza BigQuery DataFrames. Per ulteriori informazioni, consulta la documentazione di riferimento di BigQuery DataFrames.

Per autenticarti in BigQuery, configura le Credenziali predefinite dell'applicazione. Per maggiori informazioni, vedi Configurare ADC per un ambiente di sviluppo locale.

# Select model you'll use for predictions. `read_gbq_model` loads model
# data from BigQuery, but you could also use the `cluster_model` object
# from previous steps.
cluster_model = bpd.read_gbq_model(
    your_model_id,
    # For example: "bqml_tutorial.london_station_clusters",
)

# Use 'contains' function to filter by stations containing the string
# "Kennington".
stationstats = stationstats.loc[
    stationstats["station_name"].str.contains("Kennington")
]

result = cluster_model.predict(stationstats)

# Expected output results:   >>>results.peek(3)
# CENTROID...	NEAREST...	station_name  isweekday	 duration num_trips dist...
# 	1	[{'CENTROID_ID'...	Borough...	  weekday	  1110	    5749	0.13
# 	2	[{'CENTROID_ID'...	Borough...	  weekend	  2125      1774	0.13
# 	1	[{'CENTROID_ID'...	Webber...	  weekday	  795	    6517	0.16
#   3 rows × 7 columns