Classification with Logistic Regression

              
1234567891011121314151617181920212223242526
            
import urllib.request
from pyspark.sql import SparkSession
from pyspark.sql.functions import col, floor
from pyspark.ml import Pipeline
from pyspark.ml.feature import StringIndexer, VectorAssembler, StandardScaler
from pyspark.ml.classification import LogisticRegression

urllib.request.urlretrieve(
    "https://staging-content-media-cdn.codefinity.com/courses/aa80ac56-0d50-49e8-9231-2c2374cd3e9d/flights.csv",
    "flights.csv"
)

spark = SparkSession.builder \
    .appName("LogisticRegression") \
    .master("local[*]") \
    .getOrCreate()

flights_df = spark.read.csv("flights.csv", header=True, inferSchema=True) \
    .fillna(0, subset=["DEPARTURE_DELAY", "ARRIVAL_DELAY", "DISTANCE", "SCHEDULED_TIME"])

flights_df = flights_df \
    .withColumn("LABEL", (col("ARRIVAL_DELAY") > 15).cast("double")) \
    .withColumn("DEPARTURE_HOUR", floor(col("SCHEDULED_DEPARTURE") / 100).cast("integer")) \
    .withColumn("IS_WEEKEND", (col("DAY_OF_WEEK") >= 6).cast("integer"))

train_df, test_df = flights_df.randomSplit([0.8, 0.2], seed=42)

              
1234567891011
            
# Defining pipeline stages
indexer = StringIndexer(inputCol="AIRLINE", outputCol="AIRLINE_IDX")
assembler = VectorAssembler(
    inputCols=["DEPARTURE_DELAY", "DISTANCE", "SCHEDULED_TIME", "DEPARTURE_HOUR", "IS_WEEKEND", "AIRLINE_IDX"],
    outputCol="FEATURES_RAW"
)
scaler = StandardScaler(inputCol="FEATURES_RAW", outputCol="FEATURES", withMean=True, withStd=True)
lr = LogisticRegression(featuresCol="FEATURES", labelCol="LABEL", maxIter=10)

pipeline = Pipeline(stages=[indexer, assembler, scaler, lr])
model = pipeline.fit(train_df)

              
1234
            
predictions = model.transform(test_df)

# Showing label, probability, and prediction for each row
predictions.select("LABEL", "probability", "prediction").show(5)