wolframalpha

# from sklearn.metrics import f1_score, accuracy_score
import numpy as np
from collections import defaultdict


def get_metrics_cm_for_one_index(cm, index):
    n_samples = cm.ravel().sum()
    total_obs = cm[index].sum()
    tp = cm[index, index]
    fp = cm[:, index].sum() - cm[index, index]

wolframalpha

def treatoutliers(self, df=None, columns=None, factor=1.5, method='IQR', treament='cap'):
    """
    Removes the rows from self.df whose value does not lies in the specified standard deviation
    :param columns:
    :param in_stddev:
    :return:
    """
    #     if not columns:
    #         columns = self.mandatory_cols_ + self.optional_cols_ + [self.target_col]
    if not columns:

wolframalpha

# tunnel
gcloud compute ssh --zone=us-east1-b --ssh-flag="-D" --ssh-flag="10001" --ssh-flag="-N" --ssh-flag="-n" "meow-2024-m"

# run the cmd in another terminal session
 google-chrome "http://meow-2024-m:8123" \
    --proxy-server="socks5://localhost:10001" \
    --host-resolver-rules="MAP * 0.0.0.0 , EXCLUDE localhost" \
    --user-data-dir=/tmp/ &

wolframalpha

import xlrd
wb=xlrd.open_workbook("/home/wolfram/Downloads/17750_01-05-2018_10619 COC VSWR Fault.xlsx")
ws=wb.sheet_by_index(0)
data = [[col.value for col in ws.row(n_row)] for n_row in range(ws.nrows)]
print(data)

wolframalpha

import pandas as pd


chunksize = 1000
ip_filename = '/home/wolfram/Downloads/DataParserData.csv'
op_filename = 'datafile.csv'
prefix = 'cleansedquery_'

all_keys = set()
first_write = True

wolframalpha

public override string Finalize()
    {
 
//Calculating the summary statistics
       sum = rowvalue.Sum(); 
       min = rowvalue.Min();
       max = rowvalue.Max();
       count = rowvalue.Count();
       mean=rowvalue.Average();
       range=max-min;

wolframalpha

columns = ['store_id',
 'sale_type',
 'is_online_sale',
 'is_pick_up',
 'pick_up_store_id',
 'sku_id',
 'tot_unit_sold',
 'tot_promotion_price',
 'tot_reg_price',
 'tot_otd_price',

wolframalpha

from functools import reduce
rename = {
 'is_online_order': 'is_online_order',
 'pos_disc_code': 'sale_type',
 'brand': 'cat_attribute_desc_1',
 'style_code': 'style_code',
 'category_code_lvl_1': 'cat_lvl_code_1',
 'category_code_lvl_2': 'cat_lvl_code_2',
 'category_code_lvl_3': 'cat_lvl_code_3',
 'category_code_lvl_4': 'cat_lvl_code_4',

wolframalpha

#!/bin/bash
VM=$1
OPS=$2
NODES=$4
ZONE=$3

vms=($VM-m)

for (( i=0 ; i<$NODES-1; i++ ))
do

wolframalpha

from pyspark import SparkConf,SparkContext
from pyspark.sql.functions import *
from pyspark.sql import *
from pyspark.sql.types import *

configs = [('spark.eventLog.enabled', 'true'),
 ('spark.dynamicAllocation.minExecutors', '8'),
 ('spark.executor.instances', '1000'),
 ('spark.driver.host', '10.142.0.3'),
 ('spark.yarn.am.memory', '640m'),