"""
Run the column data set with K-NN algorithm
"""
import matplotlib.pyplot as plt
from src.Algorithms.Supervised.knearestneighbours import KNN
from numpy import array, arange, mean, hstack
from pandas import DataFrame
from src.Utils.utils import get_data
from src.Utils.CrossValidate import CrossValidation
if __name__ == '__main__':
accuracys = []
all_k = []
data = get_data("column_2C_weka.arff", type="arff")
data = DataFrame(data[0])
knn = KNN(data)
for realization in range(20):
knn.split()
best_k = knn.validate()
all_k.append(best_k)
knn.split()
Y_output, Y_test = knn.train(best_k)
accuracys.append(knn.test(Y_output, Y_test))
print(" # --------------------------------- #")
print("Realization: ", realization)
print("Best K: ", best_k)
print("Accuracy: ", accuracys[realization])
print("Finished")
print("Mean accuracy: ", mean(accuracys))
from numpy import zeros, concatenate, array, where, log, argmax, inf, sqrt, pi, exp, mean
from Strings import string
from sklearn.model_selection import train_test_split
from numpy.random import rand
from src.Utils.utils import sigmoid, get_data, get_confusion_matrix, plot_confusion_matrix
from sklearn.model_selection import KFold
from src.Algorithms.Supervised.NaiveBayes import NaiveBayes
if __name__ == '__main__':
data = get_data("data_banknote_authentication.txt", type="csv")
number_lines = data.shape[0]
number_columns = data.shape[1]
X = array(data, ndmin=2)[:, :number_columns - 1]
Y = array(array(data, ndmin=2)[:, number_columns - 1], ndmin=2).T
train_size = .8
test_size = .2
indices = where(Y == -1)
Y[indices] = 0
print(X)
print(Y)
acc = []
acc_eta = []
kf = KFold(n_splits=10)
eta_validation_vector = [1., 0.15, 0.1, 1e-2, 1e-3]
for realization in range(5):
x_train, x_test, y_train, y_test = train_test_split(X, Y, test_size=test_size)
import matplotlib.pyplot as plt
from numpy import reshape, array, mean
from sklearn.datasets import load_iris
from src.Utils.ColorMap import ColorMap
from matplotlib.colors import ListedColormap
from src.Utils.utils import heaveside, normalize
# just for the plot
IRIS = load_iris()
"""
Utilizando simgmoid logistica
"""
if __name__ == '__main__':
data = get_data("Iris", type='csv')
p = perceptron(data, 0.015, 500, type=2, logist=True)
p.X = normalize(p.X)
p.add_bias()
feature_names = ['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)']
target_names = array(['setosa', 'versicolor', 'virginica'], dtype='<U10')
sepal_lenth = data[0] # sepal length (cm)
sepal_width = data[1] # sepal width (cm)
# plt.figure(figsize=(10, 7))
#
# plt.hist([sepal_lenth, sepal_width], bins=20, color=["green", "red"])
# plt.title("sepal length (cm) vs sepal width (cm)")
# plt.xlabel("sepal length (cm) vs sepal width (cm)")
# plt.ylabel("Count")
# plt.show()
"""
Run the column data set with K-NN algorithm
"""
import matplotlib.pyplot as plt
from src.Algorithms.Supervised.knearestneighbours import KNN
from numpy import array, arange, mean, hstack
from pandas import DataFrame
from src.Utils.utils import get_data
from src.Utils.CrossValidate import CrossValidation
if __name__ == '__main__':
accuracys = []
data = get_data("Iris", type="csv")
data = DataFrame(data)
knn = KNN(data)
all_k = []
for realization in range(20):
knn.split()
best_k = knn.validate()
all_k.append(best_k)
knn.split()
Y_output, Y_test = knn.train(3)
accuracys.append(knn.test(Y_output, Y_test))
print(" # --------------------------------- #")
print("Realization: ", realization)
print("Best K: ", best_k)
print("Accuracy: ", accuracys[realization])
print(" # --------------------------------- #")
def pre_processing(reviews, bag, type="tr"):
Matrix = zeros((len(reviews), len(bag) + 1))
i = 0
for review, sentiment in reviews:
if str(sentiment) != 'nan' and len(sentiment.split()) == 1:
Matrix[i] = SentimentAnalisys.text_to_vector(
Matrix[i], review, int(sentiment), bag)
i += 1
return Matrix
if __name__ == '__main__':
data = get_data('chennai_reviews.csv', type='csv')
bag = (SentimentAnalisys.create_vocabulary(data[2]))
accuracys = []
accuracys_train = []
for realization in range(10):
hit = 0
reviews_train, reviews_test = train_test_split(array(data[[2, 3]])[1:],
test_size=0.2)
Matrix_train = pre_processing(reviews_train, bag)
naive = NaiveBayes(Matrix_train, reviews_train, bag, type="bernolli")
thetas_ic, thetas_c = naive.train()
for row in Matrix_train:
p = naive.test(row=row, thetas_ic=thetas_ic, thetas_c=thetas_c)
Y_output = naive.predict(p) + 1
