import pandas as pd
import numpy as np

seeding = 0

R_mu, R_sig = (16.0, 0.5)
B_mu, B_sig = (16.0, 0.2)
G_mu, G_sig = (16.4, 0.4)
P_mu, P_sig = (16.0, 0.3)
O_mu, O_sig = (16.8, 0.8)

df_config = pd.DataFrame({
    "Colour_raw":['RED','R','Red','red','BLUE','Bleu','Blue','B','G','Green','GREEN','green','O','Orang','Orange','PURP','Purpal','Purple'],
    "Colour_True" : ['Red','Red','Red','Red','Blue','Blue','Blue','Blue','Green','Green','Green','Green','Orange','Orange','Orange','Purple','Purple','Purple'],
    "N_parts" : [2301,5325,6003,8002,1200,490,4450,1151,1990,9012,342,153,5515,23,6351,741,698,4900],
    "Mu": [R_mu,R_mu,R_mu,R_mu,B_mu,B_mu,B_mu,B_mu,G_mu,G_mu,G_mu,G_mu,O_mu,O_mu,O_mu,P_mu,P_mu,P_mu],
    "Sig": [R_sig,R_sig,R_sig,R_sig,B_sig,B_sig,B_sig,B_sig,G_sig,G_sig,G_sig,G_sig,O_sig,O_sig,O_sig,P_sig,P_sig,P_sig]

})

df_mast = pd.DataFrame()
for n1 in range(0,len(df_config)):
    np.random.seed(seeding)
    df_local = pd.DataFrame(
        {'Colour':df_config.loc[n1,'Colour_raw'],
        'Length':np.round(np.random.normal(df_config.loc[n1,'Mu'],df_config.loc[n1,'Sig'],df_config.loc[n1,'N_parts']),3)})
    df_mast = pd.concat([df_mast,df_local])

Measurements = df_mast.sample(frac=1).reset_index(drop=True)
    
Tolerences = pd.DataFrame({'Colour':['Red','Blue','Green','Orange','Purple'],
                       'Lower Tolerence':[14.50,15.625,15.60,14.15,15.25],
                       'Upper Tolerence':[19.150,17.755,18.25,17.95,17.25]})

#Numberparts = df_config['N_parts'].sum()
#print (Numberparts)
    
#Red=Measurements.loc[Measurements['Colour'] == 'RED']
#print (Red)

# On homogéneise le nom de la colonne Colour_raw
df_config['Colour_raw'].loc[df_config['Colour_raw'] == 'RED'] = 'Red'
df_config['Colour_raw'].loc[df_config['Colour_raw'] == 'R'] = 'Red'
df_config['Colour_raw'].loc[df_config['Colour_raw'] == 'red'] = 'Red'
df_config['Colour_raw'].loc[df_config['Colour_raw'] == 'BLUE'] = 'Blue'
df_config['Colour_raw'].loc[df_config['Colour_raw'] == 'Bleu'] = 'Blue'
df_config['Colour_raw'].loc[df_config['Colour_raw'] == 'Blue'] = 'Blue'
df_config['Colour_raw'].loc[df_config['Colour_raw'] == 'B'] = 'Blue'
df_config['Colour_raw'].loc[df_config['Colour_raw'] == 'G'] = 'Green'
df_config['Colour_raw'].loc[df_config['Colour_raw'] == 'GREEN'] = 'Green'
df_config['Colour_raw'].loc[df_config['Colour_raw'] == 'Green'] = 'Green'
df_config['Colour_raw'].loc[df_config['Colour_raw'] == 'green'] = 'Green'
df_config['Colour_raw'].loc[df_config['Colour_raw'] == 'O'] = 'Orange'
df_config['Colour_raw'].loc[df_config['Colour_raw'] == 'Orang'] = 'Orange'
df_config['Colour_raw'].loc[df_config['Colour_raw'] == 'Orange'] = 'Orange'
df_config['Colour_raw'].loc[df_config['Colour_raw'] == 'PURP'] = 'Purple'
df_config['Colour_raw'].loc[df_config['Colour_raw'] == 'Purpal'] = 'Purple'
df_config['Colour_raw'].loc[df_config['Colour_raw'] == 'Purple'] = 'Purple'

# On homogéneise le nom de la colonne Colour     
Measurements['Colour'].loc[Measurements['Colour'] == 'RED'] = 'Red'
Measurements['Colour'].loc[Measurements['Colour'] == 'R'] = 'Red'
Measurements['Colour'].loc[Measurements['Colour'] == 'red'] = 'Red'
Measurements['Colour'].loc[Measurements['Colour'] == 'BLUE'] = 'Blue'
Measurements['Colour'].loc[Measurements['Colour'] == 'Bleu'] = 'Blue'
Measurements['Colour'].loc[Measurements['Colour'] == 'Blue'] = 'Blue'
Measurements['Colour'].loc[Measurements['Colour'] == 'B'] = 'Blue'
Measurements['Colour'].loc[Measurements['Colour'] == 'G'] = 'Green'
Measurements['Colour'].loc[Measurements['Colour'] == 'GREEN'] = 'Green'
Measurements['Colour'].loc[Measurements['Colour'] == 'Green'] = 'Green'
Measurements['Colour'].loc[Measurements['Colour'] == 'green'] = 'Green'
Measurements['Colour'].loc[Measurements['Colour'] == 'O'] = 'Orange'
Measurements['Colour'].loc[Measurements['Colour'] == 'Orang'] = 'Orange'
Measurements['Colour'].loc[Measurements['Colour'] == 'Orange'] = 'Orange'
Measurements['Colour'].loc[Measurements['Colour'] == 'PURP'] = 'Purple'
Measurements['Colour'].loc[Measurements['Colour'] == 'Purpal'] = 'Purple'
Measurements['Colour'].loc[Measurements['Colour'] == 'Purple'] = 'Purple'

#Red=Measurements.loc[Measurements['Colour'] == 'Red']
#print (Red)

##
#On extrait de df_config, l'ensemble des lignes "Red"
Red=df_config.loc[df_config['Colour_raw'] == 'Red']

#On extrait de df_config, l'ensemble des lignes "Blue"
Blue=df_config.loc[df_config['Colour_raw'] == 'Blue']

#On extrait de df_config, l'ensemble des lignes "Green"
Green=df_config.loc[df_config['Colour_raw'] == 'Green']

#On extrait de df_config, l'ensemble des lignes "Purple"
Purple=df_config.loc[df_config['Colour_raw'] == 'Purple']

#On compte le nombre d'éléments "Red"
Numberparts_Red = Red['N_parts'].sum()
print ("Numberparts_Red=", Numberparts_Red)

#On compte le nombre d'éléments "Blue"
Numberparts_Blue = Blue['N_parts'].sum()
print ("Numberparts_Blue=", Numberparts_Blue)

#On compte le nombre d'éléments "Green"
Numberparts_Green = Green['N_parts'].sum()
print ("Numberparts_Green=", Numberparts_Green)

#On compte le nombre d'éléments "Purple"
Numberparts_Purple = Purple['N_parts'].sum()
print ("Numberparts_Purple=", Numberparts_Purple)

##    
#On extrait de Measurements, l'ensemble des lignes "Purple"
Purple_M=Measurements.loc[Measurements['Colour'] == 'Purple']

#On calcule la longueur mediane des éléments Purple
#Mediane_Purple = Purple_M['Length'].median()
#print ("Mediane_Purple=", Mediane_Purple)


##    
#On extrait de Measurements, l'ensemble des lignes "Orange"
Orange_M=Measurements.loc[Measurements['Colour'] == 'Orange']

#On calcule la longueur mediane des éléments Purple
#Mediane_Orange = Orange_M['Length'].median()
#print ("Mediane_Orange=", Mediane_Orange)


##
#On extrait de Measurements l'ensemble des lignes Green
Green_M=Measurements.loc[Measurements['Colour'] == 'Green']

##
#On extrait de Measurements l'ensemble des lignes Orange
Orange_M=Measurements.loc[Measurements['Colour'] == 'Orange']


##
#On extrait de Measurements l'ensemble des lignes "Blue"
Blue_M=Measurements.loc[Measurements['Colour'] == 'Blue']

#On extrait les valeurs bleu situées entre 15,625 et 17,755
cond1_B = Blue_M.apply ( lambda row : row["Length"] >= 15.625, axis = 1 )
sub1_B = Blue_M[cond1_B]
cond2_B = sub1_B.apply ( lambda row : row["Length"] <= 17.755, axis = 1 )
sub2_B =  sub1_B[cond2_B]
#print (sub2)

#On compte le nombre de lignes dans le tableau sub2_B
N_Blue_in_tolerence = len(sub2_B)
print("N_Blue_in_tolerence=", N_Blue_in_tolerence)

#Pourcentage d'éléments dans la tolérance
percent_part_Blue = N_Blue_in_tolerence*100/Numberparts_Blue
print("%_part_Blue=", percent_part_Blue)

##
#On extrait de Measurements l'ensemble des lignes "Green"
Green_M=Measurements.loc[Measurements['Colour'] == 'Green']

#On extrait les valeurs Green situées entre 15,6 et 17,755
cond1 = Green_M.apply ( lambda row : row["Length"] >= 15.6, axis = 1 )
sub1_G = Green_M[cond1]
cond2_G = sub1_G.apply ( lambda row : row["Length"] <= 18.25, axis = 1 )
sub2_G =  sub1_G[cond2_G]
#print (sub2)

#On compte le nombre de lignes dans le tableau sub2
N_Green_in_tolerence = len(sub2_G)
print("N_Green_in_tolerence=", N_Green_in_tolerence)

#Pourcentage d'éléments dans la tolérance
percent_part_Green = N_Green_in_tolerence*100/Numberparts_Green
print("%_part_Green=", percent_part_Green)


#Différentiel des tolérances
#Tolerences["Difference"] = Tolerences['Upper Tolerence'].subtract(Tolerences['Lower Tolerence'], fill_value=0)
#print (Tolerences)


#Cacul de l'interquartile range des longueurs des éléments verts
#On importe la function iqr
from scipy.stats import iqr

#On extrait la colonne Lenght du tableau
Data_length_G = Green_M[('Length')]
print(Data_length_G)

Interquartile_G = iqr(Data_length_G)
print (Interquartile_G)


#On extrait la colonne Lenght du tableau
Data_length_O = Orange_M[('Length')]
#print(Data_length_G)

Interquartile_O = iqr(Data_length_O)
print (Interquartile_O)