노트북에서 쿼리 결과 탐색

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

# Inspect one of the columns (or series) of the DataFrame:
bq_df["body_mass_g"]

# Compute the mean of this series:
average_body_mass = bq_df["body_mass_g"].mean()
print(f"average_body_mass: {average_body_mass}")

# Find the heaviest species using the groupby operation to calculate the
# mean body_mass_g:
(
    bq_df["body_mass_g"]
    .groupby(by=bq_df["species"])
    .mean()
    .sort_values(ascending=False)
    .head(10)
)

# Create the Linear Regression model
from bigframes.ml.linear_model import LinearRegression

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

# Drop the columns we don't care about
adelie_data = adelie_data.drop(columns=["species"])

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

# Pick feature columns and label column
X = training_data[
    [
        "island",
        "culmen_length_mm",
        "culmen_depth_mm",
        "flipper_length_mm",
        "sex",
    ]
]
y = training_data[["body_mass_g"]]

model = LinearRegression(fit_intercept=False)
model.fit(X, y)
model.score(X, y)