Membuat model regresi dengan BigQuery DataFrames

from bigframes.ml.linear_model import LinearRegression
import bigframes.pandas as bpd

# Load data from BigQuery
query_or_table = "bigquery-public-data.ml_datasets.penguins"
bq_df = bpd.read_gbq(query_or_table)

# Filter down to the data to the Adelie Penguin species
adelie_data = bq_df[bq_df.species == "Adelie Penguin (Pygoscelis adeliae)"]

# Drop the species column
adelie_data = adelie_data.drop(columns=["species"])

# Drop rows with nulls to get training data
training_data = adelie_data.dropna()

# Specify your feature (or input) columns and the label (or output) column:
feature_columns = training_data[
    ["island", "culmen_length_mm", "culmen_depth_mm", "flipper_length_mm", "sex"]
]
label_columns = training_data[["body_mass_g"]]

test_data = adelie_data[adelie_data.body_mass_g.isnull()]

# Create the linear model
model = LinearRegression()
model.fit(feature_columns, label_columns)

# Score the model
score = model.score(feature_columns, label_columns)

# Predict using the model
result = model.predict(test_data)