def solve(self):
x_train, x_test, y_train, y_test = train_test_split(self.inputs, self.outputs, test_size=0.3, random_state=1)
x_train_numeric = self.getFeatures(x_train, self.repository.numericCols)
x_train_string = self.getFeatures(x_train, self.repository.stringCols)
x_test_numeric = self.getFeatures(x_test, self.repository.numericCols)
x_test_string = self.getFeatures(x_test, self.repository.stringCols)
x_train_numeric, x_test_numeric = normalisation(x_train_numeric, x_test_numeric) # normalise the numeric features
x_train_string = self.vectorizeStringFeatures(x_train_string) # convert string features to float
x_test_string = self.vectorizeStringFeatures(x_test_string)
x_train = self.unionFeatures(x_train_numeric, x_train_string)
x_test = self.unionFeatures(x_test_numeric, x_test_string)
clf_tree = tree.DecisionTreeClassifier(criterion='gini', random_state=1)
clf_tree.fit(x_train, y_train)
y_computed = clf_tree.predict(x_test)
acc = accuracy(y_computed, y_test)
print("accuracy:", acc)
from utils import loadData, splitData,flatten,normalisation
import matplotlib.image as mpimg
from sklearn import neural_network
from sklearn.metrics import accuracy_score
if __name__=="__main__":
inputs, outputs = loadData("data.csv")
trainInputs, trainOutputs, validationInputs, validationOutputs = splitData(inputs,outputs)
trainInputsFlatten = [flatten(el) for el in trainInputs]
validationInputsFlatten = [flatten(el) for el in validationInputs]
trainInputsNormalised, validationInputsNormalised = normalisation(trainInputsFlatten, validationInputsFlatten)
classifier = neural_network.MLPClassifier(hidden_layer_sizes=(5,), activation='relu', max_iter=1000, solver='sgd', verbose=10, random_state=1, learning_rate_init=.1)
classifier.fit(trainInputsNormalised,trainOutputs)
predictedLabels = classifier.predict(validationInputsNormalised)
print("Real labels: ", validationOutputs)
print("Computed labels: ", predictedLabels)
acc = accuracy_score(validationOutputs, predictedLabels)
print("Accuracy: ",acc)
import variables
import variables_image_recognition
import lime
import lime.lime_tabular
import sklearn
import sklearn.metrics
from sklearn.linear_model import LogisticRegression
from sklearn.datasets import fetch_20newsgroups
from lime.lime_text import LimeTextExplainer
from utils_lime import Draw_Lime_On_Logistic_Regression
exit()
if variables.choice_of_work == 1:
xtrain, ytrain, xtest, ytest = load_data(variables.file_name)
xtrain, xtest = normalisation(xtrain, xtest)
n = NN(variables.choice, variables.w)
n.fit(xtrain, ytrain)
ypred = n.pred(xtest)
print(1 - accuracy_score(ytest, ypred))
explainer = lime.lime_tabular.LimeTabularExplainer(xtrain,
mode='classification')
exp = explainer.explain_instance(xtest[0],
n.pred_proba,
labels=1,
top_labels=1)
exp.as_pyplot_figure()
plt.show()
elif variables.choice_of_work == 2:
xtrain, ytrain, xtest, ytest = load_data(variables.file_name)
xtrain, xtest = normalisation(xtrain, xtest)
from utils import loadData, splitData, normalisation, transform, myNormalisation
from sklearn import linear_model
from sklearn.metrics import accuracy_score
if __name__ == "__main__":
#step 1. load data
inputs, outputs = loadData("iris.data")
#step 2. split data
trainInputs, trainOutputs, validationInputs, validationOutputs = splitData(
inputs, outputs)
#step 3. normalisation
normalisedTrainData, normalisedTestData = normalisation(
trainInputs, validationInputs)
#step 4. training
classifier = linear_model.LogisticRegression()
classifier.fit(normalisedTrainData, transform(trainOutputs))
#step 5. make predictions
computedTestOutputs = classifier.predict(normalisedTestData)
#step 6. evalaute the classifier performance
print("Computed outputs", computedTestOutputs)
print("Real outputs", transform(validationOutputs))
error = 1 - accuracy_score(transform(validationOutputs),
computedTestOutputs)
print("classification error (tool): ", error)
feature1 = [ex[0] for ex in inputs] #Economy..GDP.per.Capita.
feature2 = [ex[1] for ex in inputs] #Freedom
#train and test samples normalised
import numpy as np
np.random.seed()
indexes = [i for i in range(len(inputs))]
trainSample = np.random.choice(indexes, int(0.8 * len(inputs)), replace=False)
testSample = [i for i in indexes if not i in trainSample]
trainInputs = [inputs[i] for i in trainSample]
trainOutputs = [outputs[i] for i in trainSample]
testInputs = [inputs[i] for i in testSample]
testOutputs = [outputs[i] for i in testSample]
trainInputs, testInputs = normalisation(trainInputs, testInputs)
trainOutputs, testOutputs = normalisation(trainOutputs, testOutputs)
feature1train = [ex[0] for ex in trainInputs]
feature2train = [ex[1] for ex in trainInputs]
feature1test = [ex[0] for ex in testInputs]
feature2test = [ex[1] for ex in testInputs]
#using sklearn tool:
from sklearn import linear_model
from sklearn.metrics import mean_squared_error
regressor = linear_model.SGDRegressor(alpha=0.01, max_iter=1000, average=True)
regressor.fit(trainInputs, trainOutputs)
w0, w1, w2 = regressor.intercept_[0], regressor.coef_[0], regressor.coef_[1]
print('the learnt model: f(x1,x2) = ', w0, ' + ', w1, ' * x1', '+', w2, '*x2')