airbnb_load_data

listings_path = 'your_path/listings.csv'
reviews_path = 'your_path/reviews.csv'

listings_df = spark.read \
  .option('multiLine', 'True') \
  .option('escape', '"') \
.option("mode", "DROPMALFORMED")\
  .csv(listings_path, header=True)

reviews_scheme = StructType([StructField('listing_id', IntegerType(), True),
                             StructField('id', IntegerType(), True),
                             StructField('date', DateType(), True),
                             StructField('reviewer_id', IntegerType(), True),
                             StructField('reviewer_name', StringType(), True),
                             StructField('comments', StringType(), True)])
reviews_df = spark.read \
  .option('multiLine', 'True') \
  .option('escape', '"') \
.option("mode", "DROPMALFORMED")\
  .csv(reviews_path, header=True, schema=reviews_scheme)