gabefair

import pandas as pd
from pymongo import MongoClient

client = MongoClient("mongodb://localhost:27017")
db = client.database_Name

collection_conn = db['collection_name']
collection_cursor = collection_conn.find()
collection_pandas_df = pd.DataFrame(list(collection_cursor))

nmukerje

from pyspark.sql.types import *
from pyspark.sql.functions import *

#Flatten array of structs and structs
def flatten(df):
   # compute Complex Fields (Lists and Structs) in Schema   
   complex_fields = dict([(field.name, field.dataType)
                             for field in df.schema.fields
                             if type(field.dataType) == ArrayType or  type(field.dataType) == StructType])
   while len(complex_fields)!=0:

bradtraversy

MongoDB Cheat Sheet

Show All Databases

show dbs

Show Current Database

fahadsiddiqui

def flattenDataFrame(df: DataFrame): DataFrame = {
  val fields = df.schema.fields
  val fieldNames = fields.map(x => x.name)

  for (i <- fields.indices) {
    val field = fields(i)
    val fieldType = field.dataType
    val fieldName = field.name
    fieldType match {
      case _: ArrayType =>