#
#   Copyright (C) 2020 Alessandro Languasco
#
import pandas as pd
import numpy as np 
#import mpmath as mp 
#mp.dps = 38
    
# open output file 
file= open("../analysis.txt","w")

# functions needed to create the normalised values
def f(x): 
    #mp.dps = 38
    #x1 = mp.mpmathify(x)
    #y = mp.log(x1)
    y= np.log(x)
    return y

# input data from csv file    
data=pd.read_csv(r'ekek+.csv', sep=';',dtype='str')
data.head(4)
df = pd.DataFrame(data, columns= ['q','EK','EK+','vq'])
df = df.astype('float128')

# create a new column with normalised EK values
df['normEK'] = (df['EK'] / f(df['q']) )
#df['normEK'] = mp.fdiv( df['EK'] , f(df['q']) )
# create a new column with normalised EK+ values
df['normEK+'] = (df['EK+'] / f(df['q']) )
#df['normEK+'] = mp.fdiv( df['EK+'] , f(df['q']) ) 

#print (df)

#FINDING MAX AND MIN and where they are attained
#M=df['min'].max()
#idxM=df['min'].idxmax()
#argM=df['q'].iloc[idxM]
#m=df['min'].min()
#idxm=df['min'].idxmin()
#argm=df['q'].iloc[idxm]

#print('minimal value on column min =',m,'attained at q =',argm)
#print('maximal value on column min =',M,'attained at q =',argM)


#FINDING MAX and second MAX; MIN and second MIN; and where they are attained

print(' *****   Statistics for EK, EK+  *****')
print('name source file = ekek+.csv')

file.write(" *****   Statistics for EK, EK+ ***** ")
file.write("\n")
file.write("name source file = ekek+.csv")
file.write("\n")

print(' *****   MAX normalised values EK/log(q) *****')
 
maxima =df['normEK'].nlargest(2)
M=maxima.iloc[0]
idxM=maxima.idxmax()
argM=df['q'].iloc[idxM]
M1=maxima.iloc[1]
idxM1=maxima.idxmin()
argM1=df['q'].iloc[idxM1]
print('maximal value on column normEK =','{0:.16f}'.format(M),'attained at q =',argM)
print('second maximal value on column normEK =','{0:.16f}'.format(M1),'attained at q =',argM1)

file.write("  *****   MAX  normalised values EK/log(q) *****\n")
file.write("maximal value on column normEK = ")
file.write(str('{0:.16f}'.format(M)))
file.write(" attained at q = ")
file.write(str(argM))
file.write("\n")
file.write("second maximal value on column normEK = ")
file.write(str('{0:.16f}'.format(M1)))
file.write(" attained at q = ")
file.write(str(argM1))
file.write("\n")
 

print(' *****   MIN normalised values EK/log(q) *****') 
minima =df['normEK'].nsmallest(2)
m=minima.iloc[0]
idxm=minima.idxmin()
argm=df['q'].iloc[idxm]
m1=minima.iloc[1]
idxm1=minima.idxmax()
argm1=df['q'].iloc[idxm1]
print('minimal value on column normEK =','{0:.16f}'.format(m),'attained at q =',argm)
print('second minimal value on column normEK =','{0:.16f}'.format(m1),'attained at q =',argm1)

file.write("  *****   Min normalised values EK/log(q) *****\n")
file.write("minimal value on column normEK = ")
file.write(str('{0:.16f}'.format(m)))
file.write(" attained at q = ")
file.write(str(argm))
file.write("\n")
file.write("second minimal value on column normEK = ")
file.write(str('{0:.16f}'.format(m1)))
file.write(" attained at q = ")
file.write(str(argm1))
file.write("\n")

print(' *****   MAX normalised values EK+/log(q) *****')
 
maxima =df['normEK+'].nlargest(2)
M=maxima.iloc[0]
idxM=maxima.idxmax()
argM=df['q'].iloc[idxM]
M1=maxima.iloc[1]
idxM1=maxima.idxmin()
argM1=df['q'].iloc[idxM1]
print('maximal value on column normEK+ =','{0:.16f}'.format(M),'attained at q =',argM)
print('second maximal value on column normEK+ =','{0:.16f}'.format(M1),'attained at q =',argM1)

file.write("  *****   MAX  normalised values EK+/log(q) *****\n")
file.write("maximal value on column normEK+ = ")
file.write(str('{0:.16f}'.format(M)))
file.write(" attained at q = ")
file.write(str(argM))
file.write("\n")
file.write("second maximal value on column normEK+ = ")
file.write(str('{0:.16f}'.format(M1)))
file.write(" attained at q = ")
file.write(str(argM1))
file.write("\n")
 

print(' *****   MIN normalised values EK+/log(q) *****') 
minima =df['normEK+'].nsmallest(2)
m=minima.iloc[0]
idxm=minima.idxmin()
argm=df['q'].iloc[idxm]
m1=minima.iloc[1]
idxm1=minima.idxmax()
argm1=df['q'].iloc[idxm1]
print('minimal value on column normEK+ =','{0:.16f}'.format(m),'attained at q =',argm)
print('second minimal value on column normEK+ =','{0:.16f}'.format(m1),'attained at q =',argm1)

file.write("  *****   Min normalised values EK+/log(q) *****\n")
file.write("minimal value on column normEK+ = ")
file.write(str('{0:.16f}'.format(m)))
file.write(" attained at q = ")
file.write(str(argm))
file.write("\n")
file.write("second minimal value on column normEK+ = ")
file.write(str('{0:.16f}'.format(m1)))
file.write(" attained at q = ")
file.write(str(argm1))
file.write("\n")

print(' *****   STATS for EK, EK+ (colored points)   *****')

# number of  colored points 
total=float(len(df))
orange = len(df.loc[df.vq <= 0.25])
green = len(df.loc[df.vq <= 0.5]) - orange
blue = len(df.loc[df.vq <= 0.75]) - (orange+green)
black = len(df.loc[df.vq <= 1]) - (orange+green+blue)
red = len(df.loc[df.vq > 1])
percentorange=float(orange)/total
percentgreen=float(green)/total
percentblue=float(blue)/total
percentblack=float(black)/total
percentred=float(red)/total
print('number of orange points:', orange,'percentage =', percentorange*100)
print('number of green points:', green,'percentage =', percentgreen*100)
print('number of blue points:', blue,'percentage =', percentblue*100)
print('number of black points:', black,'percentage =', percentblack*100)
print('number of red points:', red,'percentage =', percentred*100)


file.write("  *****   STATS for EK, EK+ (colored points)   *****\n")
file.write("number of orange points: ")
file.write(str(orange))
file.write(" percentage = ")
file.write(str(percentorange*100))
file.write("\n")
file.write("number of green points: ")
file.write(str(green))
file.write(" percentage = ")
file.write(str(percentgreen*100))
file.write("\n")
file.write("number of blue points: ")
file.write(str(blue))
file.write(" percentage = ")
file.write(str(percentblue*100))
file.write("\n")
file.write("number of black points: ")
file.write(str(black))
file.write(" percentage = ")
file.write(str(percentblack*100))
file.write("\n")
file.write("number of red points: ")
file.write(str(red))
file.write(" percentage = ")
file.write(str(percentred*100))
file.write("\n")
  
print('total colored numbers =', orange+green+blue+black+red) 
print('total numbers (number of rows) =', int(total)) 

file.write("total colored numbers = ")
file.write(str(orange+green+blue+black+red))
file.write("\n") 
file.write("total numbers (number of rows) = ")
file.write(str(int(total)))
file.write("\n")

print(' *****   Exported data frame for gnuplot   *****')
print(' *****   in file named: dati-totali-per-grafico.txt  *****')
# remove the normalised columns
del df['normEK'] 
del df['normEK+'] 
df.to_csv (r'dati-totali-per-grafico.txt', sep='\t', index = False, header=True)


print(' *****   End analysis script   *****')
file.write("*****   End analysis script   *****")
file.close()