#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Sat Dec 30 20:02:22 2017

@author: Kamessi
"""

import csv
import numpy as np
from scipy import linalg as LA

def read_country(filename):
    f = open(filename,'r', encoding='utf-8')
    reader = csv.reader(f)
    raw_matrix = []
    for row in reader:
        temp = []
        for i in range(0,len(row)):
            try:
                temp.append(float(row[i]))
            except ValueError:
                temp.append(row[i])
        raw_matrix.append(temp)  
    f.close()
    return raw_matrix


def main():
    #Read the raw matrix
    raw_matrix = read_country("2009.csv")
    
    #compute mcp
    product_list = raw_matrix[0][1::]
    country_list = []
    for i in range(1,len(raw_matrix)):
        country_list.append(raw_matrix[i][0])
    
    country_sum = []
    for i in range(1,len(raw_matrix)):
        country_sum.append(np.sum(raw_matrix[i][1::]))
    
    product_sum = []
    for i in range(1,len(raw_matrix[0])):
        product = 0
        for j in range(1,len(raw_matrix)):
            product += raw_matrix[j][i]
        product_sum.append(product)
    total_sum = np.sum(product_sum)
    
    mcp = []
    
    for i in range (1,len(raw_matrix)):
        country_row = []
        for j in range(1,len(raw_matrix[i])):
            percentage = raw_matrix[i][j]/country_sum[i-1]
            total_percentage = product_sum[j-1]/total_sum
            if percentage > total_percentage:
                country_row.append(1)
            else:
                country_row.append(0)
        mcp.append(country_row)
    
    #compute mpp
    country_sum = []
    for i in range(0,len(mcp)):
        country_sum.append(np.sum(mcp[i]))
    
    product_sum = []
    for i in range(0,len(mcp[0])):
        product = 0
        for j in range(0,len(mcp)):
            product += mcp[j][i]
        product_sum.append(product)
    total_sum = np.sum(product_sum)
    
    mpp = []
    for i in range(0,len(mcp[0])):
        product_row = []
        for j in range(0,len(mcp[0])):
            temp_sum = 0
            for k in range(0,len(mcp)):
                try:
                    temp_sum += (mcp[k][i] * mcp[k][j]/(country_sum[k]*product_sum[i]))
                except:
                    pass
            product_row.append(temp_sum)
        mpp.append(product_row)
    
    #compute PCI
    mpp = np.array(mpp)
    
    e_vals, e_vecs = LA.eig(mpp)
    eigenvectors = e_vecs.tolist()
    eigen = []
    for eigenvector in eigenvectors:
        temp = []
        for col in eigenvector:
            temp.append(col.real)
        eigen.append(temp)
    
    vector = []
    for i in range(0,len(eigen)):
        vector.append(eigen[i][1])
    
    pci = []
    if vector[len(vector)-2] > 0:
        for item in vector:
            pci.append((item-np.mean(vector))/np.std(vector))
    else:
        for item in vector:
            pci.append((-item+np.mean(vector))/np.std(vector))
    
    #compute proximity
    proximity = []
    for i in range(0,len(mcp[0])):
        product_row = []
        for j in range(0,len(mcp[0])):
            temp_sum = 0
            for k in range(0,len(mcp)):
                try:
                    temp_sum += mcp[k][i] * mcp[k][j]
                except:
                    pass
            p0 = product_sum[i]
            p1 = product_sum[j]
            if p0 < p1:
                large = p1
            else:
                large = p0
            product_row.append(temp_sum/large)
        proximity.append(product_row)
    
    #compute actual distance
    distance1 = []
    for i in range(0,len(mcp)):
        product_row = []
        for j in range(0,len(mcp[0])):
            sum1 = 0
            for k in range(0,len(mcp[0])):
                if k != j:
                    try:
                        sum1 += mcp[i][k]*proximity[j][k]
                    except:
                        pass
            sum2 = 0
            for k in range(0,len(mcp[0])):
                if k != j:
                    try:
                        sum2 += proximity[j][k]
                    except:
                        pass
            product_row.append(1-sum1/sum2)
        distance1.append(product_row)
    
    distance1 = np.array(distance1)
    d1 = np.transpose(distance1)
    
    matrix = open("actual distance 1.csv",'w',newline='')
    writer = csv.writer(matrix)
    country_list = ["Product"] + country_list
    writer.writerow(country_list)
    for i in range(0,len(d1)):
        temp = [product_list[i]]
        temp.extend(d1[i])
        writer.writerow(temp)
    matrix.close()
    
    #Read the raw matrix
    raw_matrix = read_country("2014.csv")
    
    #compute mcp
    product_list2 = raw_matrix[0][1::]
    country_list2 = []
    for i in range(1,len(raw_matrix)):
        country_list2.append(raw_matrix[i][0])
    
    country_sum = []
    for i in range(1,len(raw_matrix)):
        country_sum.append(np.sum(raw_matrix[i][1::]))
    
    product_sum = []
    for i in range(1,len(raw_matrix[0])):
        product = 0
        for j in range(1,len(raw_matrix)):
            product += raw_matrix[j][i]
        product_sum.append(product)
    total_sum = np.sum(product_sum)
    
    mcp = []
    
    for i in range (1,len(raw_matrix)):
        country_row = []
        for j in range(1,len(raw_matrix[i])):
            percentage = raw_matrix[i][j]/country_sum[i-1]
            total_percentage = product_sum[j-1]/total_sum
            if percentage > total_percentage:
                country_row.append(1)
            else:
                country_row.append(0)
        mcp.append(country_row)
    
    #compute mpp
    country_sum = []
    for i in range(0,len(mcp)):
        country_sum.append(np.sum(mcp[i]))
    
    product_sum = []
    for i in range(0,len(mcp[0])):
        product = 0
        for j in range(0,len(mcp)):
            product += mcp[j][i]
        product_sum.append(product)
    total_sum = np.sum(product_sum)
    
    mpp = []
    for i in range(0,len(mcp[0])):
        product_row = []
        for j in range(0,len(mcp[0])):
            temp_sum = 0
            for k in range(0,len(mcp)):
                try:
                    temp_sum += (mcp[k][i] * mcp[k][j]/(country_sum[k]*product_sum[i]))
                except:
                    pass
            product_row.append(temp_sum)
        mpp.append(product_row)
    
    #compute PCI
    mpp = np.array(mpp)
    
    e_vals, e_vecs = LA.eig(mpp)
    eigenvectors = e_vecs.tolist()
    eigen = []
    for eigenvector in eigenvectors:
        temp = []
        for col in eigenvector:
            temp.append(col.real)
        eigen.append(temp)
    
    vector = []
    for i in range(0,len(eigen)):
        vector.append(eigen[i][1])
    
    pci = []
    if vector[len(vector)-2] > 0:
        for item in vector:
            pci.append((item-np.mean(vector))/np.std(vector))
    else:
        for item in vector:
            pci.append((-item+np.mean(vector))/np.std(vector))
    
    #compute proximity
    proximity = []
    for i in range(0,len(mcp[0])):
        product_row = []
        for j in range(0,len(mcp[0])):
            temp_sum = 0
            for k in range(0,len(mcp)):
                try:
                    temp_sum += mcp[k][i] * mcp[k][j]
                except:
                    pass
            p0 = product_sum[i]
            p1 = product_sum[j]
            if p0 < p1:
                large = p1
            else:
                large = p0
            product_row.append(temp_sum/large)
        proximity.append(product_row)
    
    #compute actual distance
    distance2 = []
    for i in range(0,len(mcp)):
        product_row = []
        for j in range(0,len(mcp[0])):
            sum1 = 0
            for k in range(0,len(mcp[0])):
                if k != j:
                    try:
                        sum1 += mcp[i][k]*proximity[j][k]
                    except:
                        pass
            sum2 = 0
            for k in range(0,len(mcp[0])):
                if k != j:
                    try:
                        sum2 += proximity[j][k]
                    except:
                        pass
            product_row.append(1-sum1/sum2)
        distance2.append(product_row)
    
    distance2 = np.array(distance2)
    d2 = np.transpose(distance2)
    
    matrix = open("actual distance 2.csv",'w',newline='')
    writer = csv.writer(matrix)
    country_list2 = ["Product"] + country_list2
    writer.writerow(country_list2)
    for i in range(0,len(d2)):
        temp = [product_list2[i]]
        temp.extend(d2[i])
        writer.writerow(temp)
    matrix.close()
    
    #calculate ADI
    adi = []
    
    if len(distance1[0]) == len(distance2[0]):
        print("categorization verified")
    
    common = []
    for i in range(1,len(country_list)):
        if country_list[i] in country_list2:
            for j in range(1,len(country_list2)):
                if country_list[i] == country_list2[j]:
                    common.append(country_list[i])
                    temp = []
                    for k in range(0,len(distance1[0])):
                        temp.append(distance2[j-1][k]-distance1[i-1][k])
                    adi.append(temp)
    
    adi = np.array(adi)
    adi = np.transpose(adi)
    
    matrix = open("ADI.csv",'w',newline='')
    writer = csv.writer(matrix)
    common = ["Product"] + common
    writer.writerow(common)
    for i in range(0,len(adi)):
        temp = [product_list2[i]]
        temp.extend(adi[i])
        writer.writerow(temp)
    matrix.close()
    

if __name__ == "__main__":
    main()