aialenti

#   Read the source tables in Parquet format
sales_table = spark.read.parquet("./data/sales_parquet")

'''
-- Create a temporary table with a few renamings
CREATE TABLE temp_1 AS
SELECT seller_id AS the_seller,
       num_pieces_sold AS pieces,
       product_id
FROM sales_table;

aialenti

#   Read the source tables in Parquet format
sales_table = spark.read.parquet("./data/sales_parquet")

'''
SELECT product_id,
       SUM(num_pieces_sold) AS total_pieces_sold,
       AVG(num_pieces_sold) AS average_pieces_sold,
       MAX(num_pieces_sold) AS max_pieces_sold_of_product_in_orders,
       MIN(num_pieces_sold) AS min_pieces_sold_of_product_in_orders,
       COUNT(num_pieces_sold) AS num_times_product_sold

aialenti

#   Read the source tables in Parquet format
sales_table = spark.read.parquet("./data/sales_parquet")

'''
SELECT order_id AS the_order_id,
       seller_id AS the_seller_id,
       num_pieces_sold AS the_number_of_pieces_sold
FROM sales_table
'''
#   Execution Plan and show action in one line

aialenti

#   Read the source tables in Parquet format
sales_table = spark.read.parquet("./data/sales_parquet")

'''
SELECT *
FROM sales_table
'''
#   Execution Plan
sales_table_execution_plan = sales_table.select(col("*"))
#   Show (Action) - Showing 5 rows with no limit in columns width

aialenti

# Import Spark
import pyspark
from pyspark.sql import SparkSession
from pyspark.sql.functions import *

#   Initialize the Spark session
spark = SparkSession.builder \
    .master("local") \
    .appName("SparkLikeABoss") \
    .getOrCreate()

aialenti

//  Import Spark
import org.apache.spark.sql._
import org.apache.spark.sql.functions._

//  Create Spark Session
val spark = SparkSession.builder.
      master("local")
      .appName("spark session example")
      .getOrCreate()

aialenti

import pandas as pd
import enchant
import nltk
from tqdm import tqdm
from nltk.corpus import stopwords
from nltk.tokenize import RegexpTokenizer

#   Declare tokenizers
punctuation_tokenizer = RegexpTokenizer(r'[^\sA-Za-z0-9]')
numbers_tokenizer = RegexpTokenizer(r'[0-9]')

aialenti

from tensorflow.keras.applications.resnet50 import ResNet50
from tensorflow.keras.preprocessing import image
from tensorflow.keras.applications.resnet50 import preprocess_input
import numpy as np
import os
from sklearn.manifold import TSNE
from sklearn.decomposition import PCA
from PIL import Image
import pandas as pd
import pickle

aialenti

aialenti

%%javascript
window.buildChartSelect(element)
window.buildControls(element)