from sklearn.linear_model import RidgeClassifier

print(__doc__)

# Code source: Gaël Varoquaux

#              Andreas Müller

# Modified for documentation by Jaques Grobler

# License: BSD 3 clause

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

from matplotlib.colors import ListedColormap

from sklearn.model_selection import train_test_split

from sklearn.preprocessing import StandardScaler

from sklearn.datasets import make_moons, make_circles, make_classification

from sklearn.neural_network import MLPClassifier

from sklearn.neighbors import KNeighborsClassifier

from sklearn.svm import SVC

from sklearn.gaussian_process import GaussianProcessClassifier

from sklearn.gaussian_process.kernels import RBF

from sklearn.tree import DecisionTreeClassifier

from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier

from sklearn.naive_bayes import GaussianNB

from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis, LinearDiscriminantAnalysis

h = .02  # step size in the mesh

names = ["KNN", "Linear SVM",

         "Naive Bayes", "LDA", "QDA"]

classifiers = [

    KNeighborsClassifier(),

    SVC(kernel="linear", C=0.025),

    GaussianNB(),

    LinearDiscriminantAnalysis(),

    QuadraticDiscriminantAnalysis()]

train_original = pd.read_csv("DataUsed/method23_real2.csv")

test_original = pd.read_csv("DataUsed/method23_real2_valid.csv")

df = train_original.append(test_original, ignore_index=True)

# df.insert(3, "num2", num2)

targetIndex = -1

# df = df.iloc[pd.isna(df.iloc[:, targetIndex]).values == False, :]

# df = df.drop(columns=["Num1"])

vars = df.columns[range(len(df.columns) - 1)]

df = df.values

X1 = df[:, [0, -2]]

X2 = df[:, [0, -6]]

X3 = df[:, [-6, -2]]

y = df[:, targetIndex]

datasetsNames = ["450,810 nm", "450, 610 nm", "610,810 nm"]

C450810 = (X1, y)

C450610 = (X2, y)

C610810 = (X3, y)

datasets = [C450810, C450610, C610810]

figure = plt.figure(figsize=(27, 9))

i = 1

# iterate over datasets

for ds_cnt, ds in enumerate(datasets):

    # preprocess dataset, split into training and test part

    X, y = ds

    X = StandardScaler().fit_transform(X)

    X_train, X_test, y_train, y_test = \

        train_test_split(X, y, test_size=.8)

    x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5

    y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5

    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),

                         np.arange(y_min, y_max, h))

    # just plot the dataset first

    cm = plt.cm.RdBu

    cm_bright = ListedColormap(['#FF0000', '#0000FF'])

    ax = plt.subplot(len(datasets), len(classifiers) + 1, i)

    if ds_cnt == 0:

        ax.set_title("Input data")

    # Plot the training points

    ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,

               edgecolors='k')

    # Plot the testing points

    ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6,

               edgecolors='k')

    ax.set_xlim(xx.min(), xx.max())

    ax.set_ylim(yy.min(), yy.max())

    ax.set_xticks(())

    ax.set_yticks(())

    ax.set_ylabel(datasetsNames[ds_cnt])

    i += 1

    # iterate over classifiers

    for name, clf in zip(names, classifiers):

        ax = plt.subplot(len(datasets), len(classifiers) + 1, i)

        clf.fit(X_train, y_train)

        score = clf.score(X_test, y_test)

        # Plot the decision boundary. For that, we will assign a color to each

        # point in the mesh [x_min, x_max]x[y_min, y_max].

        if hasattr(clf, "decision_function"):

            Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])

        else:

            Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]

        # Put the result into a color plot

        Z = Z.reshape(xx.shape)

        ax.contourf(xx, yy, Z, cmap=cm, alpha=.8)

        # Plot the training points

        ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,

                   edgecolors='k')

        # Plot the testing points

        ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright,

                   edgecolors='k', alpha=0.6)

        ax.set_xlim(xx.min(), xx.max())

        ax.set_ylim(yy.min(), yy.max())

        ax.set_xticks(())

        ax.set_yticks(())

        if ds_cnt == 0:

            ax.set_title(name)

        ax.text(xx.max() - .3, yy.min() + .3, ('Accuracy: %.2f' % score).lstrip('0'),

                size=15, horizontalalignment='right')

        i += 1

plt.tight_layout()

plt.show()

pass