humamfauzi

import numpy as np

def approx_distribution(array):
    array = np.array(array)
    array.sort()
    radii = np.std(array)
    array_size = len(array)
    max_val = np.max(array)
    min_val = np.min(array)
    container = np.zeros(array_size)

humamfauzi

package main

import "fmt"

// If function want to take any dtype, use interface{}. We can iterate it using for range
func threeDotsInterface(a ...interface{}) {
  for k, v := range a {
    fmt.Println("Key ", k, " Value ", v)
  }
}

humamfauzi

package main

import (
  "math/rand"
  "time"
  "log"
)

func randomArray(n int) []int {
   array := make([]int, n)

humamfauzi

package main

// Merge function is based from https://github.com/tmrts/go-patterns with little modification

import (
  "sync"
  "fmt"
  "math/rand"
)

humamfauzi

package car

import "fmt"

type Speed float64
const (
  MPH Speed = 1
  KPH Speed = 1.60934
)

humamfauzi

package main

import "fmt"

func main() {
  var address0 *int
  var number int
  number = 32
  address0 = &number
  fmt.Println("Address ::", address0, "Value", number)

humamfauzi

This is example how wait group works. Main objective of wait group is control concurrency. In vanilla.go, we have ordinary program without concurrency. The goal of each program is creating numbers of random integer, count total numbers of each numbers and print it with its ratios respective to total numbers created.

When we apply go goroutine, Go does not wait for the process to complete to proceed (non-blocking). While it is a good thing for execution speed, non-blocking process can be messed up as in no_waitgroup. Here come the wait group. Wait group have three methods which is .Add(), .Done(), Wait(). The first we use .Add() with input of how many process must be done before waiting is over. .Done() is a way telling the wait group that a process has been done. .Wait() halt the process unless all process done which indicated by number of .Done() executed is equal to .Add() input.

humamfauzi

package main

import (
  "fmt"
  "math/rand"
  "sync"
  "time"
)

func main() {

humamfauzi

# Please use Jupyter notebook to test this.

from sklearn.datasets import samples_generator
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import AdaBoostClassifier, BaggingClassifier, VotingClassifier
from sklearn.model_selection import StratifiedKFold, GridSearchCV, train_test_split
import numpy as np
import pandas as pd

X, y = samples_generator.make_classification(n_samples = 5000, 

humamfauzi

def describe_dataframe(dataframe):
#    Create a dictionary which have every detected categorical value counts in a dataframe and NaN ratio 
    describe_df = {}
    for j in dataframe.dtypes.value_counts().index:
        describe_dict = {}
        cols = dataframe.select_dtypes(str(j)).columns
        for i in cols:
            if dataframe[i].nunique() < 100:
                describe_dict[str(i)] = {"total_category": dict(dataframe[i].value_counts()), 
                                         "NaN_ratio": dataframe[i].isnull().sum()/float(dataframe.shape[0])}