import numpy as np
from sklearn.naive_bayes import GaussianNB
from sklearn import metrics
import pickle
import os
import pandas as pd
from sklearn.preprocessing import MinMaxScaler

# def prediction_generator(list_):
#     # This method need a np. array.
#     # Therefore this method needs the imports:
#     # import pandas as pd
#     # import pickle
#     # In the folder models.py
#     # @return one it with the prediction
#     vanilla_df = pd.read_excel("small_set_normalized_21_04_2020_2.xlsx",encoding='utf-8')
#     LOrdinalCols = ['Competitiveness_Score', 'Openness', 'Conscentiousness',
#                'Agreeableness', 'Neuroticism', 'Extraversion']
#     scaler = MinMaxScaler()
#     scaler.fit(vanilla_df[LOrdinalCols])
#     list_[LOrdinalCols] = scaler.transform(list_[LOrdinalCols])
#     #------------- TODO:Preprocessing done. Add the classifier with pickle --------#
#     x = np.asarray(list_, dtype=np.float32)
#     print(list_)
#     print(x)
#     #x = np.asarray(list_, dtype=np.float32)
#
#     # --------------
#     # Create model
#     # --------------
#     sfilename = os.getcwd()+'/'+'model_NaiveBayses-70.19acc.sav'
#     # load the model from disk
#     model = pickle.load(open(sfilename, 'rb'))
#
#     x = x.reshape(1, -1)
#
#     y_pred = model.predict(x)
#
#     iY_pred = int(y_pred)
#
#     return iY_pred

def prediction_human_expert(list_):
    # REQUIRED LIST FORM
    # feats_ = ['Competitiveness_Score', 'Openness','Conscentiousness', 'Agreeableness', 'Neuroticism', 'Extraversion',
    #           'younger_siblings', 'older_siblings', 'english_lk', 'math_lk', 'risksq001','parental_home_german', 'parental_home_foreign_language',
    #           'birthplace_Baden-Wuerttemberg', 'birthplace_Bayern', 'birthplace_Hessen', 'birthplace_Nordrhein-Westfalen',
    #           'degree_mother_Universitaet','degree_father_Universitaet','birthplace_Rheinland-Pfalz', 'birthplace_other',
    #           'age_before_85', 'age_85_89', 'age_90_94', 'age_95_99', 'age_00_later', 'gender', 'impatiencesq001']
    # [4., 4., 6., 7., 2., 3., 1., 0., 0., 0., 6., 0., 1., 0., 0., 1., 0., 1., 1., 0., 1., 1., 0., 0., 0., 0., 0., 6.]

    x = np.asarray(list_, dtype=np.float32).reshape(1, -1)
    if x.mean() > 5:
        return 1
    else:
        return 0

    #sfilename = os.getcwd()+'/'+'model_.sav'
    #load the model from disk
    #model = pickle.load(open(sfilename, 'rb'))
    #y_pred = model.predict(x)


def prediction_ml(list_):

    #sfilename = os.getcwd()+'/'+'RF_model_.sav'
    sfilename = '/Users/kev/Desktop/oTree_/Mirror_mirror/RF_model_.sav'
    model = pickle.load(open(sfilename, 'rb'))

    x = np.asarray(list_, dtype=np.float32).reshape(1, -1)
    y_pred = model.predict_proba(x)[:,1][0]
    #print(y_pred)
    if y_pred > 0.6:
        return 1
    else:
        return 0