thangarajan8

import pandas as pd
import numpy as np
import json
f_path = "HomePage.java"
with open(f_path,'r') as f:
    content = f.read()
def flattern_json(d):
    if len(d) == 0:
        return {}

thangarajan8

import pandas as pd
import numpy as np
import json
f_path = "ContactsPage.java"
with open(f_path,'r') as f:
    content = f.read()
#def flattern_json(d):
#    if len(d) == 0:
#        return {}

thangarajan8

import datetime
# text = "april 23 january 11 2020"
text = "enero 01 diciembre 31 2020"


def multi_date_text(text):
  month_dict = {"enero":"january","febrero":"february","marzo":"march","abril":"april",
              "mayo":"may","junio":"june","julio":"july","agosto":"august",
              "septiembre":"september","octubre":"october","noviembre":"november","diciembre":"december"}
  text = [month_dict[i]  if i.lower() in month_dict.keys() else i for i in text.split(" ") ]

thangarajan8

from pyspark.sql.types import *

# Auxiliar functions
# Pandas Types -> Sparks Types
def equivalent_type(f):
  if f == 'datetime64[ns]': return DateType()
  elif f == 'int64': return LongType()
  elif f == 'int32': return IntegerType()
  elif f == 'float64': return FloatType()
  else: return StringType()

thangarajan8

from pyspark.sql import SparkSession
from pyspark.sql.functions import col, sum as spark_sum, when

# Initialize Spark session
# spark = SparkSession.builder \
#     .appName("Sales Analysis") \
#     .getOrCreate()

# Sample data
data = [

thangarajan8

from pyspark.sql import SparkSession
from pyspark.sql.functions import col, udf, expr, hour,format_number
from pyspark.sql.types import LongType
import pandas as pd

# Initialize Spark session
spark = SparkSession.builder.appName("DateDifference").getOrCreate()

def exclude_weekends_and_jan1(start_date, end_date):
    # Create a date range

thangarajan8

def clean_amount(value):
    # Move trailing minus to the front
    value = value.replace('-', '')
    is_negative = value.endswith('-') or value.startswith('-')

    # Remove thousand separator and convert decimal separator
    value = value.replace('.', '').replace(',', '.').replace('-', '')

    # Convert to float
    try: