KaleabTessera

# Load model with best rMse and make prediction
fileName = "results/" + "bestRegressionModel_" + str(LineaReggressionMetrics.ROOT_MEAN_SQUARED_ERROR.name) + ".sav"
bestRegression = joblib.load(fileName)

#Example ICO
#Format - price_usd,price_btc,total_supply,market_cap_usd,available_supply,usd_raised,eth_price_launch,btc_price_launch,ico_duration,month,day,country
example_x = np.array([1.71456,0.00019931,1000000000,905793616,528295082,24000000,297.63,3420.4,7,8,9,182])

y_pred = makePrediction(bestRegression,example_x)
print("Predicted value of example ICO after six months: ",y_pred )

KaleabTessera

# Function which will be called to make a prediction
def makePrediction(model,example_to_predict):
    # One-hot encode the example to match the data it was trained on.
    encoded_x = encodeSingleElement(x,example_to_predict)
    y_pred = model.predict(encoded_x.reshape(1, -1))
    
    return y_pred

# Load model with best rMse and make prediction
fileName = "results/" + "bestRegressionModel_" + str(LineaReggressionMetrics.ROOT_MEAN_SQUARED_ERROR.name) + ".sav"

KaleabTessera

#!/bin/bash
 
MONGO_DATABASE="your_db_name"
APP_NAME="your_app_name"
HOST_NAME="host_name_or_localhost"
USERNAME="username_database"
PASSWORD="password_database"

MONGO_HOST="127.0.0.1"
MONGO_PORT="27017"

KaleabTessera

import numpy as np 

#This function retrieves all subsets in a set recursively.
def findSubsets(allSubsets,subset,currentIndex,maxSubsetSize):      
    if(len(subset) == currentIndex):
        return allSubsets
    
    newSet = []
    for i in range(0,len(allSubsets)):
      if(len(allSubsets[i]) < maxSubsetSize):

KaleabTessera

#!/bin/bash
chosenVPNServer=za8.nordvpn.com.udp.ovpn
cd /etc/openvpn
cd ovpn_udp
ls -al
sudo openvpn $chosenVPNServer

KaleabTessera

#!/bin/bash
sudo apt-get install openvpn
cd /etc/openvpn
sudo wget https://downloads.nordcdn.com/configs/archives/servers/ovpn.zip
sudo apt-get install ca-certificates
sudo apt-get install unzip
sudo unzip ovpn.zip
sudo rm zip