import pandas
from pandas.plotting import scatter_matrix
from pandas.plotting import andrews_curves
import matplotlib.pyplot as plt
from sklearn import model_selection
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
import pyodbc as cn
import numpy as np
import pandas as pd
from sklearn import preprocessing


class Program:


    #url = "https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data"
    # url = "C:\\Users\\rajmu\\Desktop\\iris.data"
    #names = ['sepal-length', 'sepal-width', 'petal-length', 'petal-width', 'class']
    validation_size = -1
    seed = -1

    def __init__(self):
        #self.dataset = pandas.read_csv(Program.url, names=Program.names)

        #Connecting to database
        server = 'facil.database.windows.net'
        database = 'main'
        username = 'facildatabase'
        password = 'DifficultPassword69.'
        driver = '{ODBC Driver 11 for SQL Server}'
        cnxn = cn.connect('DRIVER=' + driver + ';SERVER=' + server + ';DATABASE=' + database + ';UID=' + username + ';PWD=' + password)
        print(cnxn)

        ##Importing Data to dataframes form daatabase
        nutsComplete = pd.read_sql('SELECT * from dbo.NutsComplete', con = cnxn)
        boltsComplete = pd.read_sql('SELECT * from dbo.BoltsComplete', con = cnxn)
        contracts = pd.read_sql('SELECT * from dbo.contracts', con = cnxn)
        coatings = pd.read_sql('SELECT * from dbo.coatings', con = cnxn)
        geometryCoating = pd.read_sql('SELECT * from dbo.geometryCoating', con = cnxn)
        countryCodes = pd.read_sql('SELECT * from dbo.countryCodes', con = cnxn)
        rfqPortal = pd.read_sql('SELECT * from dbo.rfqPortal', con = cnxn)

        headers = list(nutsComplete)

        nutsComplete['Has_Washer'] = nutsComplete['Has_Washer'].astype('category')
        nutsComplete['plantNumber'] = nutsComplete['plantNumber'].astype('category')

        self.dataset = nutsComplete

    def info(self):
        print(self.dataset.shape)
        print(self.dataset.describe())

    def show_sample(self, amt=10):
        print(self.dataset.head(amt))

    def show_whisker_plots(self):
        self.dataset.plot(kind="box", subplots=True, layout=(1, 4), sharex=False, sharey=False)
        plt.show()

    def show_histogram(self):
        # histograms
        self.dataset.hist()
        plt.show()

    def show_matrix(self):
        scatter_matrix(self.dataset)
        plt.show()

    def show_curves(self):
        andrews_curves(self.dataset, 'class')
        plt.show()

    def __split_validation_dataset(self):
        array = self.dataset.values
        X = array[:, 0:4]
        Y = array[:, 4]
        Program.validation_size = 0.5
        Program.seed = 7
        return model_selection.train_test_split(X, Y, test_size=Program.validation_size, random_state=Program.seed)

    def test_models(self):
        X_train, X_validation, Y_train, Y_validation = Program.__split_validation_dataset(self)
        scoring = 'accuracy'
        models = []
        models.append(('LR', LogisticRegression()))
        models.append(('LDA', LinearDiscriminantAnalysis()))
        models.append(('KNN', KNeighborsClassifier()))
        models.append(('CART', DecisionTreeClassifier()))
        models.append(('NB', GaussianNB()))
        models.append(('SVM', SVC()))
        # evaluate each model in turn
        results = []
        names = []
        for name, model in models:
            kfold = model_selection.KFold(n_splits=10, random_state=Program.seed)
            cv_results = model_selection.cross_val_score(model, X_train, Y_train, cv=kfold, scoring=scoring)
            results.append(cv_results)
            names.append(name)
            msg = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
            print(msg)
        # visualize test data
        fig = plt.figure()
        fig.suptitle('Alg comparison')
        ax = fig.add_subplot(111)
        plt.boxplot(results)
        ax.set_xticklabels(names)
        plt.show()

    def predict_with_knn(self):
        knn = KNeighborsClassifier()
        x_train, x_validation, y_train, y_validation = Program.__split_validation_dataset(self)
        knn.fit(x_train, y_train)
        predictions = knn.predict(x_validation)
        print(accuracy_score(y_validation, predictions))
        print(confusion_matrix(y_validation, predictions))
        print(classification_report(y_validation, predictions))


def main():
    p = Program()
    #p.test_models()
    p.predict_with_knn()
    p.show_histogram()


if __name__ == "__main__":
    main()