import pandas as pd
import os
from sklearn.manifold import TSNE
import matplotlib.pyplot as plt
import numpy as np

from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
import imp
import sys
sys.path.insert(0, 'PyLib')

#A modified library from the internet suitet to this demonstration
import plot_confusion_matrix_compact 
imp.reload(plot_confusion_matrix_compact)
from plot_confusion_matrix_compact import plot_confusion_matrix

#The mentioned library
import model_score_plot
imp.reload(model_score_plot)
from model_score_plot import ModelScorePlot as MSP

#Library to merge dataframes and show a tSNE image
import df_proc
imp.reload(df_proc)
from df_proc import *

csvDir='CSVs'
beef_df=pd.read_csv(csvDir+'/'+'beef_df_100g.csv',sep=',',index_col=0)
fish_df=pd.read_csv(csvDir+'/'+'fish_df_100g.csv',sep=',',index_col=0)
veg_df=pd.read_csv(csvDir+'/'+'veg_df_100g.csv',sep=',',index_col=0)
fruit_df=pd.read_csv(csvDir+'/'+'fruit_df_100g.csv',sep=',',index_col=0)
dfL=[beef_df,fish_df,fruit_df,veg_df]
typesL=['beef','fish','fruit','vegetable']
colorL=['black','blue','red','green']
colorL=['black','blue','red','green']
dataDic=combineDfs(iDfL=dfL,typesL=typesL,colorL=colorL,figSize=(50,50),iDpi=80,plotText=False)

dataDic['df'].head(3)

cols=list(dataDic['df'].columns.values)
colsX=cols.copy()
colsX.remove('type')
labels=list(set(dataDic['df']['type'].values))
print(cols)
print(labels)
print(colsX)
X=dataDic['df'][colsX].values
y=dataDic['df']['type'].values
for i,t in enumerate(labels):
    y[y==t]=i
y=y.flatten().astype(int)
X=X.astype(float)

mms=MinMaxScaler()
Xn=mms.fit_transform(X)

msp = MSP()

knc_df=msp.kncScores(Xn,y,cv=5,param_name='n_neighbors',paramRange=(1,100,1),trainW=1,testW=2,title='KNC',plot=True)

knc_df

svc_df=msp.svcScores(Xn,y,cv=5,param_name='C',max_iter=50000,degrees=(2,4,1),paramRange=(100,1000,100),plot=True)

svc_df

dtc_df=msp.dtcScores(Xn,y,cv=5,param_name='max_depth',paramRange=(1,10,1),trainW=1,testW=2,title='Decision Tree classifier',plot=True)
dtc_df

rfc_df=msp.rfcScores(Xn,y,cv=5,param_name='max_depth',estimatorsRange=(2,11,1),paramRange=(1,15,1),trainW=1,testW=2,title='Randorm Forest classifier',clfArg={},plot=True)

rfc_df

abc_df=msp.abcScores(Xn,y,cv=5,param_name='n_estimators',paramRange=(1,10,1),trainW=1,testW=2,title='Adaboost classifier',clfArg={},plot=True)

abc_df

models=[knc_df,svc_df,dtc_df,rfc_df,abc_df]
pd.concat(models).sort_values(by='weighted_score',ascending=False)

X_train, X_test, y_train, y_test = train_test_split(Xn,y)
rfc=RFC(max_depth=14,n_estimators=7)
rfc.fit(X_train,y_train)
y_pred=rfc.predict(X_test)
conf_matr=confusion_matrix(y_test, y_pred)
print(confusion_matrix(y_test, y_pred))
print(classification_report(y_test, y_pred,target_names=labels))

plot_confusion_matrix(conf_matr,labels,normalize=False)

models_df=msp.modelsCalculation(Xn,y,abc={'paramRange':(2,20,2)},rfc={'estimatorsRange':(10,20,1),'paramRange':(1,20,1)},dtc={'paramRange':(1,20,1)})
models_df