import numpy as np
import math
import matplotlib.patches as mpatches
from mpl_toolkits.mplot3d import Axes3D
from matplotlib.pyplot import figure, xticks,plot, title, xlabel, ylabel, show, xlim, ylim, legend, scatter, subplot, tight_layout, grid, annotate

def readFile (fileString, numberOfAttributes, numberOfObservations):
    returnArray = np.full((numberOfObservations, numberOfAttributes), '',dtype = 'object')
    counter = 0 # Is a incrementing counter, keepin track of position in current row
    for i in range (numberOfObservations): # Goes through all observations of the data set
        for j in range (numberOfAttributes): # Goes through all attributes of the data set
            while (True):
                if counter == len(fileString):
                    return returnArray
                if fileString[counter] == ',': # checks, if next attribute is present
                    counter += 1
                    break # skips to next attribute
                else:
                    returnArray[i,j] = str(returnArray[i,j]) + str(fileString[counter])
                    counter += 1
    return returnArray

#Loading and reading file
observations = 194
attributes = 30
test = open('flag.txt')
text = test.read()
dataInArray = readFile(text, attributes, observations)

def outOfK (inputArray, numberOfAttributes, numberOfObservations):
    lengthOfOutOfK = np.ones(30)
    lengthOfOutOfK[1]= 6
    lengthOfOutOfK[2] = 4
    lengthOfOutOfK[5] = 10
    lengthOfOutOfK[6] = 7
    lengthOfOutOfK[17] = 7
    lengthOfOutOfK[28] = 7
    lengthOfOutOfK[29] = 7
    returnArray = np.zeros((194,71)) # creates returnArray
    returnCount = 0
    for i in range (numberOfAttributes):
        if i == 0:
            returnCount = returnCount
        elif i in (1,2,5,6,17,28,29): # defines the positions to do 1-out-of-K
            for j in range (int(lengthOfOutOfK[i])):
                if i in (1,2,5,6): # already defined
                    if i == 6:
                        for h in range (194):
                            returnArray[h,returnCount + int((inputArray[h,i]))] = 1
                    else:
                        for h in range (194):
                            returnArray[h,returnCount + int((inputArray[h,i])) - 1] = 1
                elif i in (17,28,29): # colors
                    for h in range (194): # goes through all observations
                        if inputArray[h,i] == 'red':
                            returnArray[h,returnCount] = 1
                        if inputArray[h,i] == 'green':
                            returnArray[h,returnCount+1] = 1
                        if inputArray[h,i] == 'blue':
                            returnArray[h,returnCount+2] = 1
                        if inputArray[h,i] == 'gold':
                            returnArray[h,returnCount+3] = 1
                        if inputArray[h,i] == 'white':
                            returnArray[h,returnCount+4] = 1
                        if inputArray[h,i] == 'black':
                            returnArray[h,returnCount+5] = 1
                        if inputArray[h,i] in ('orange', 'brown'):
                            returnArray[h,returnCount+6] = 1
        else:
            returnArray[:,returnCount] = inputArray[:,i]
        if i == 1:
            returnCount += 5
        elif i == 2:
            returnCount += 3
        elif i == 5:
            returnCount += 9
        elif i in (6,17,28,29):
            returnCount += 6
        returnCount += 1
    returnArray = np.delete(returnArray, 0, 1) # removes attribute of countries
    returnArray = np.delete(returnArray, np.array([5,6,7,8,9,10,11]), 1) # removes attribute of religion
    returnArray = np.delete(returnArray, 3, 1) # removes attribute of population

    return returnArray

dataOutOfK_ALL = outOfK(dataInArray, attributes, observations)

outOfKAttributes = np.array(['Landmass','Geographic quadrant','Area[km2]','Population[millions]','Language','Religion','Bars'
                             , 'Stripes','colours','red','green','blue','gold','white','black','orange/brown','predominant colour',
                             'Circles','Crosses','Saltires','Quarters','Sunstars','Crecent moon','Triangle','Icon','Animate','text',
                             'Topleft-colour','Bottomright-colour'])

definingLandmass = np.array(['North America','South America','Europe','Africa','Asia','Oceania'])
definingZone = np.array(['NE','SE','SW','NW'])
#definingArea
definingPopulation = np.array(['<1m', '1-5m','6-10m','11-20m','21-50m','>50m'])
definingLanguage = np.array(['English','Spanish','French','German','Slavic','Other European','Chineses','Arabic','Japenese, \nTurkish, \nMagyar','Others'])
definingReligion = np.array(['Catholic','Other Christian','Muslim','Buddhist','Hindu','Ethnic','Marxist'])




### SETUP FOR STATISTICS ###
# Set 'columnnumber' to the desired column to investigate
# Set 'tal' to:
#       1: if number
#       0: if text

columnnumber = 1
tal = 1

# Ejects the desired data
if (tal == 1):
    vektorTest = dataInArray[:, columnnumber].astype(np.int)
else:
    vektorTest = dataInArray[:, columnnumber]

# print means/variance etc.





### SETUP FOR PCA FOR ALL ###

# Doing PCA with normalising for 'Flag'
#1) Subtracts mean from each and devides med standard deviation
for i in range(len(dataOutOfK_ALL[0, :])):
    if (i >= 0 and i <= 5): # Landmass
        dataOutOfK_ALL[:, i] = (dataOutOfK_ALL[:, i] - np.mean(dataOutOfK_ALL[:, i])) / math.sqrt(6)
    elif (i >= 6 and i <= 9): # zone
        dataOutOfK_ALL[:, i] = (dataOutOfK_ALL[:, i] - np.mean(dataOutOfK_ALL[:, i])) / math.sqrt(4)
    elif (i >= 11 and i <= 20): # language
        dataOutOfK_ALL[:, i] = (dataOutOfK_ALL[:, i] - np.mean(dataOutOfK_ALL[:, i])) / math.sqrt(10)
    elif (i >= 30 and i <= 36): # Mainhue
        dataOutOfK_ALL[:, i] = (dataOutOfK_ALL[:, i] - np.mean(dataOutOfK_ALL[:, i])) / math.sqrt(7)
    elif (i >= 59):
        dataOutOfK_ALL[:, i] = (dataOutOfK_ALL[:, i] - np.mean(dataOutOfK_ALL[:, i])) / math.sqrt(7)
    else:
        dataOutOfK_ALL[:, i] = (dataOutOfK_ALL[:, i] - np.mean(dataOutOfK_ALL[:, i])) / np.std(dataOutOfK_ALL[:, i])