mick001

# Set a seed
set.seed(500)

library(MASS)
data <- Boston

# Check that no data is missing
apply(data,2,function(x) sum(is.na(x)))

# Train-test random splitting for linear model

mick001

#Load library mass and set seed
library(MASS)
set.seed(100)

# We are going to use 3 random variables
m <- 3

# Number of samples to be drawn
n <- 2000

mick001

# Using airquality dataset
data <- airquality
data[4:10,3] <- rep(NA,7)
data[1:5,4] <- NA

# Removing categorical variables
data <- airquality[-c(5,6)]
summary(data)

#-------------------------------------------------------------------------------

mick001

# Copula class

import numpy as np
import matplotlib.pyplot as plt
from copulalib.copulalib import Copula
from scipy.stats import norm
plt.style.use('ggplot')

class copulaClass(object):

mick001

# Load the raw training data and replace missing values with NA
training.data.raw <- read.csv('train.csv',header=T,na.strings=c(""))

# Output the number of missing values for each column
sapply(training.data.raw,function(x) sum(is.na(x)))

# Quick check for how many different values for each feature
sapply(training.data.raw, function(x) length(unique(x)))

# A visual way to check for missing data

mick001

# Imports

import os
import sys
import time
import psutil
import logging
import pyautogui as pgui
from datetime import datetime

mick001

import numpy as np
import matplotlib.pyplot as plt
from copulalib.copulalib import Copula
plt.style.use('ggplot')

def generateData():
    global x,y
    x = np.random.normal(size=250)
    y = 2.5*x + np.random.normal(size=250)

mick001

# A simple Markov chain model for the weather in Python

import numpy as np
import random as rm
import time

# Let's define the statespace
states = ["Sunny","Cloudy"]

# Possible sequences of events

mick001

# The following code takes as input a string of text, and then it outputs the barplot of the
# frequencies of occurrence of letters in the string.
import pylab as pl
import numpy as np

string1 = """ Example string """

alphabet = ["a","b","c","d","e","f","g","h","i","j","k","l","m","n","o","p","q","r","s","t","u","v","w","x","y","z",".",",",";","-","_","+"]

# The following functon takes a list and a string of characters, it calculates how often a certain character appears

mick001

import math
from bigfloat import *
import matplotlib.pyplot as plt
from visual import *

# A class to handle the time ranges
class timeHoursSeconds(object):
    def __init__(self,s,h,d,y):
        self.s = s
        self.h = h