def recommend_movies(movie_query, k_recommendations):
raw_movies_data = []
with open('Movie_Recommender/movies_recommendation_data.csv', 'r') as md:
# Discard the first line (headings)
next(md)
# Read the data into memory
for line in md.readlines():
data_row = line.strip().split(',')
raw_movies_data.append(data_row)
# Prepare the data for use in the knn algorithm by picking
# the relevant columns and converting the numeric columns
# to numbers since they were read in as strings
movies_recommendation_data = []
for row in raw_movies_data:
data_row = list(map(float, row[2:]))
movies_recommendation_data.append(data_row)
# Use the KNN algorithm to get the 5 movies that are most
# similar to The Post.
recommendation_indices, _ = knn(movies_recommendation_data,
movie_query,
k=k_recommendations,
distance_fn=euclidean_distance,
choice_fn=lambda x: None)
movie_recommendations = []
for _, index in recommendation_indices:
movie_recommendations.append(raw_movies_data[index])
return movie_recommendations
def main():
x, y = preprocess('student-mat.csv')
print(x.shape, y.shape)
# 70%的数据用于训练
num_training = int(0.7 * len(x))
num_test = len(x) - num_training
x_train = x[:num_training]
y_train = y[:num_training]
x_test = x[num_training:]
y_test = y[num_training:]
# 01化
# normalizex(x_train, num_training)
normalizey(y_train, num_training)
# normalizex(x_test, num_test)
normalizey(y_test, num_test)
'''
import matplotlib.pyplot as plt
temp0x0 = []
temp0x1 = []
temp1x0 = []
temp1x1 = []
for i in range(len(x)):
if y[i]:
temp1x0.append(x[i][0])
temp1x1.append(x[i][1])
else:
temp0x0.append(x[i][0])
temp0x1.append(x[i][1])
plt.plot(temp1x0, temp1x1, 'g^', temp0x0, temp0x1, 'bs')
plt.axis([0, 21, 0, 21])
plt.xlabel('x0')
plt.ylabel('x1')
plt.show()
'''
#选择算法
if sys.argv[1] == 'knn':
print('KNN')
for k in range(1, 21):
hit_cnt, f1socre, y_test_pre = knn(k, 2, x_test, y_test, x_train,
y_train)
print('K = ', k, ', hit rate = ', hit_cnt / num_test, 'f1score = ',
f1socre)
elif sys.argv[1] == 'svm':
print('SVM')
normalize0(y_train)
normalize0(y_test)
testRbf(200, x_train, y_train, x_test, y_test)
for C in range(8):
hit_cnt, f1socre, y_test_pre = testRbf(200, x_train, y_train,
x_test, y_test)
print('C = ', C, ', hit rate = ', hit_cnt / num_test, 'f1score = ',
f1socre)
else:
print('Naive Bayes')
hit_cnt, f1socre, y_test_pre = bayes(x_train, y_train, x_test, y_test)
print('hit rate = ', hit_cnt / num_test, 'f1score = ', f1socre)
def main():
train_file = 'train.txt'
test_file = 'test.txt'
bayes_accuracy = naive_bayes(train_file, test_file)
knn_accuracy = knn(train_file, test_file, k=5)
dt_accuracy, tree = decision_tree(train_file, test_file)
with open('output.txt', 'w') as f:
print_tree(tree, f)
f.write('\n{}\t{}\t{}\n'.format(round(dt_accuracy, 2),
round(knn_accuracy, 2),
round(bayes_accuracy, 2)))
# Creating model objects
model = args.model
if (model == "baseline"):
model_obj = BaseLine(reviews, categories)
elif (model == "logreg"):
model_obj = LogReg(reviews)
elif (model == "multinomialNB"):
model_obj = NaiveBayes(reviews, "multinomial")
elif (model == "lda"):
model_obj = TopicModel(reviews)
elif (model == "kNearestNeighbors"):
model_obj = knn(reviews, target)
else: # put additional models here.
print("Argument Error: invalid model specified")
sys.exit()
model_classified = [] # classifications stored here
reviews = [] # resetting reviews list to save memory
# Reading test data into reviews list
if args.invert == "False":
for classifier in categories:
with open("spring-" + classifier + ".json") as json_file:
for line in json_file:
json_obj = json.loads(line)
reviews += [(classifier, json_obj)]
KNN_TRAIN = "_SUBMIT_KNN.csv"
KNN_TRAIN_BN = "_SUBMIT_KNN_BN.csv"
RESULTADO = "Prediccion.csv"
bn_transformar(TRAIN,TRAIN_BN)
bn_transformar(TEST, TEST_BN)
ampliar_set(TRAIN, TRAIN_AMPLIADO)
ampliar_set(TRAIN_BN, TRAIN_AMPLIADO_BN)
rf(TRAIN_AMPLIADO, TEST, RF_TRAIN_AMPLIADO)
rf(TRAIN_AMPLIADO_BN, TEST_BN, RF_TRAIN_AMPLIADO_BN)
knn(TRAIN, TEST, KNN_TRAIN)
knn(TRAIN_BN, TEST_BN, KNN_TRAIN_BN)
submits = [KNN_TRAIN, KNN_TRAIN_BN, RF_TRAIN_AMPLIADO_BN, RF_TRAIN_AMPLIADO]
i_mejorPredictor = 0
democratizar(submits, RESULTADO, i_mejorPredictor)
b = timeit.default_timer()
secs = b - a
m, s = divmod(secs,60)
m = int(m)
s = int(s)
print "Fin digit_recognizer (" + str( m) + ":" + str(s ) + ")"
negFeatureFolders.append(
[negFeature[j] for j in sequence[:posNum]])
#print(np.array(negFeatureFolders).shape)
for i in range(folderNum):
subTrainFeature = negFeatureFolders[i]
subTrainFeature.extend(posFeature)
subTrainFeature = np.array(subTrainFeature)
subTrainLabel = list(np.zeros(posNum))
subTrainLabel.extend(list(np.ones(posNum)))
subTrainLabel = np.array(subTrainLabel)
print("=====%dst Bagging=====") % (i + 1)
print("Positive: %d, Negative: %d") % (list(subTrainLabel).count(1),
list(subTrainLabel).count(0))
#print(subTrainFeature.shape)
#print(subTrainLabel)
predictedLabel_temp1 = knn(subTrainFeature, subTrainLabel, testFeature,
5)
predictedLabel_temp2 = decision_Tree(subTrainFeature, subTrainLabel,
testFeature)
predictedLabel_temp3 = adboostDT(subTrainFeature, subTrainLabel,
testFeature)
predictedLabel_temp4 = RandomForest_Classifer(subTrainFeature,
subTrainLabel,
testFeature)
predictedLabel_temp5 = svmclassifier(subTrainFeature, subTrainLabel,
testFeature, 1.0, 0.015625)
predictedLabel_temp6 = logistic_regression(subTrainFeature,
subTrainLabel, testFeature)
predictedLabel_voting1.append(predictedLabel_temp1)
predictedLabel_voting2.append(predictedLabel_temp2)
predictedLabel_voting3.append(predictedLabel_temp3)
#Set k, tolerance and max interations
k = 6
tolerance = 0.0001 # only for k means
max_iterations = 300 # only for k means
# k-means clustering
# get the optimal amount of clusters
dataset = np.delete(dataset, -1,
axis=1) # delete feature column to run k means clustering
#dataset = dataset[:,:-2]
km = K_Means(k, tolerance, max_iterations)
km.fit(dataset)
create_kmeans_csv(km.classes.items())
print(
len(km.classes.items()), "clusters created from the k-means algorithm. \n"
"Check k-means.csv for more information")
# KNN
flag = False
while not flag:
k = input_k("Enter k to run the KNN algorithm!").response
if k is 0 or k is "":
flag = True
print("Didn't execute algorithm")
else:
k = int(k)
print("returned value is:", k)
predictions = knn(X_train, X_test, k)
create_knn_csv(X_test)
import numpy as np
import pandas as pd
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from KNN import knn
df = datasets.load_iris()
X, y = df.data, df.target
X_train, x_test, Y_train, y_test = train_test_split(X,
y,
train_size=0.75,
random_state=42)
Model = knn()
Model.fit(X_train, Y_train)
y_preds = Model.predict(x_test)
# Model accuracy score
print(f"model accuracy score is, {accuracy_score(y_test, y_preds)}")
KNN_TRAIN = "_SUBMIT_KNN.csv"
KNN_TRAIN_BN = "_SUBMIT_KNN_BN.csv"
RESULTADO = "Prediccion.csv"
bn_transformar(TRAIN, TRAIN_BN)
bn_transformar(TEST, TEST_BN)
ampliar_set(TRAIN, TRAIN_AMPLIADO)
ampliar_set(TRAIN_BN, TRAIN_AMPLIADO_BN)
rf(TRAIN_AMPLIADO, TEST, RF_TRAIN_AMPLIADO)
rf(TRAIN_AMPLIADO_BN, TEST_BN, RF_TRAIN_AMPLIADO_BN)
knn(TRAIN, TEST, KNN_TRAIN)
knn(TRAIN_BN, TEST_BN, KNN_TRAIN_BN)
submits = [KNN_TRAIN, KNN_TRAIN_BN, RF_TRAIN_AMPLIADO_BN, RF_TRAIN_AMPLIADO]
i_mejorPredictor = 0
democratizar(submits, RESULTADO, i_mejorPredictor)
b = timeit.default_timer()
secs = b - a
m, s = divmod(secs, 60)
m = int(m)
s = int(s)
print "Fin digit_recognizer (" + str(m) + ":" + str(s) + ")"
for i in range(folderNum):
random.shuffle(sequence)
negFeatureFolders.append([negFeature[j] for j in sequence[:posNum]])
#print(np.array(negFeatureFolders).shape)
for i in range(folderNum):
subTrainFeature = negFeatureFolders[i]
subTrainFeature.extend(posFeature)
subTrainFeature = np.array(subTrainFeature)
subTrainLabel = list(np.zeros(posNum))
subTrainLabel.extend(list(np.ones(posNum)))
subTrainLabel = np.array(subTrainLabel)
print("=====%dst Bagging=====") % (i+1)
print("Positive: %d, Negative: %d") % (list(subTrainLabel).count(1), list(subTrainLabel).count(0))
#print(subTrainFeature.shape)
#print(subTrainLabel)
predictedLabel_temp1 = knn(subTrainFeature, subTrainLabel, testFeature, 5)
predictedLabel_temp2 = decision_Tree(subTrainFeature, subTrainLabel, testFeature)
predictedLabel_temp3 = adboostDT(subTrainFeature, subTrainLabel, testFeature)
predictedLabel_temp4 = RandomForest_Classifer(subTrainFeature, subTrainLabel, testFeature)
predictedLabel_temp5 = svmclassifier(subTrainFeature, subTrainLabel, testFeature, 1.0, 0.015625)
predictedLabel_temp6 = logistic_regression(subTrainFeature, subTrainLabel, testFeature)
predictedLabel_voting1.append(predictedLabel_temp1)
predictedLabel_voting2.append(predictedLabel_temp2)
predictedLabel_voting3.append(predictedLabel_temp3)
predictedLabel_voting4.append(predictedLabel_temp4)
predictedLabel_voting5.append(predictedLabel_temp5)
predictedLabel_voting6.append(predictedLabel_temp6)
print("KNN=====%dst predicted labels:") % (i+1)
print(predictedLabel_temp1)
print("DT=====%dst predicted labels:") % (i+1)
# Creating model objects
model = args.model
if (model == "baseline"):
model_obj = BaseLine(reviews, categories)
elif (model == "logreg"):
model_obj = LogReg(reviews)
elif (model == "multinomialNB"):
model_obj = NaiveBayes(reviews, "multinomial")
elif (model == "lda"):
model_obj = TopicModel(reviews)
elif (model == "kNearestNeighbors"):
model_obj = knn(reviews,target)
else: # put additional models here.
print("Argument Error: invalid model specified")
sys.exit()
model_classified = [] # classifications stored here
reviews = [] # resetting reviews list to save memory
# Reading test data into reviews list
if args.invert == "False":
for classifier in categories:
with open("spring-"+classifier+".json") as json_file:
for line in json_file:
json_obj = json.loads(line)
reviews += [(classifier,json_obj)]
def orient(name, filename, model_file, model):
if name == 'train':
if model == 'nearest' or model == 'best':
train = pd.read_csv(filename, sep=' ', header=None)
filename_knn = model_file
file = open(filename_knn, 'wb')
pickle.dump(train, file)
if model == 'nnet':
train = pd.read_csv(filename, sep=' ', header=None)
x_train = train.drop(columns=[0, 1], axis=1)
y_train = train[1]
y_train = pd.get_dummies(y_train)
y_columns = y_train.columns
x_train = x_train.to_numpy()
y_train = y_train.to_numpy()
print(x_train.shape[0], 'train samples')
a = nn(25, 0.001, 0.9)
(w1, w2, w3, b1, b2, b3) = a.fit(x_train, y_train)
weights = {
'w1': w1,
'w2': w2,
'w3': w3,
'b1': b1,
'b2': b2,
'b3': b3,
'y_columns': y_columns
}
filename_nn = model_file
file = open(filename_nn, 'wb')
pickle.dump(weights, file)
if model == 'tree':
dtreemain(name, filename, model_file)
if name == 'test':
if model == 'nearest' or model == 'best':
file = open(model_file, 'rb')
train = pickle.load(file)
test = pd.read_csv(filename, sep=' ', header=None)
X_test = test.drop(columns=[0, 1], axis=1)
y_filenames = test[0]
y_test = test[1]
X_test = X_test.to_numpy()
y_test = y_test.to_numpy()
obj = knn(10)
ypred = obj.predict(train, X_test)
f = open("output.txt", "w")
for i in range(len(X_test)):
with open('output.txt', 'a') as f:
f.write(str(y_filenames[i]) + ' ' + str(ypred[i]) + '\n')
if model == 'tree':
dtreemain(name, filename, model_file)
if model == 'nnet':
test = pd.read_csv(filename, sep=' ', header=None)
x_test = test.drop(columns=[0, 1], axis=1)
y_test = test[1]
y_filenames = test[0]
y_test = pd.get_dummies(y_test)
x_test = x_test.to_numpy()
y_test = y_test.to_numpy()
print(x_test.shape[0], 'test samples')
file = open(model_file, 'rb')
new_weights = pickle.load(file)
w1f = new_weights['w1']
w2f = new_weights['w2']
w3f = new_weights['w3']
b1f = new_weights['b1']
b2f = new_weights['b2']
b3f = new_weights['b3']
y_columns = new_weights['y_columns']
a = nn(25, 0.001, 0.9)
y_test_predicted = a.predict(x_test, w1f, w2f, w3f, b1f, b2f, b3f)
zero_one = (y_test_predicted == y_test_predicted.max(
axis=1)[:, None]).astype(int)
diff = (y_test == zero_one).sum(axis=1)
accuracy = np.count_nonzero(diff == y_test.shape[1])
print('accuracy ', accuracy / diff.shape[0] * 100)
f = open("Output.txt", "w")
for i in range(len(x_test)):
with open('Output.txt', 'a') as f:
f.write(
str(y_filenames[i]) + ' ' +
str(y_columns[np.argmax(y_test_predicted[i])]) + '\n')
from KNN import knn trainData = <path to train data> testData = <path to test data> categoricalIndices = <list of indices of any non-numerical rows> test = knn() test.trainDataProcess(trainData, categoricalIndices) test.testDataProcess(testData, True) test.predict(5)
from KNN import knn
from RandomForest import randomforest
from SupportVector import supportvector
knn=knn()
b=knn.info()
a=knn.kn()
rf=randomforest()
b=rf.rf()
sv=supportvector()
c=sv.svc()
print("Accuracy of KNN is : "+str(a))
print("Accuracy of RandomForest is : "+str(b))
print("Accuracy of SupportVector is : "+str(c))
def get_recommended_movies(self, data, fav_movie):
"""Run the k-nearest neighbors algorithm"""
recommended_movies = knn(data, fav_movie, k=5)
return recommended_movies
data_y.append(row[0]) # |
data_x = hp.normalize(data_x) # Normaliza
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# The THING itself
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
ratio = 0.40 # Known base %
k = 3 # K
distance_func = 'euclidean'
bound = int(ratio * len(data_y))
# The classification algorithm
my_output_labels = knn(x_train=data_x[:bound],
y_train=data_y[:bound],
x_test=data_x[bound + 1:],
distance=distance_func,
k=k)
print('Objective: ' + str(data_y[bound + 1:]))
print('Obtained: ' + str(my_output_labels))
# Matriz de Confusão
i = 0
tp, tn, fp, fn = 0, 0, 0, 0
for label in data_y[bound + 1:]:
if label == my_output_labels[
i] and label == 'Iris-setosa': # True Positive
tp += 1
elif label == my_output_labels[
i] and label == 'Iris-versicolor': # True Negative
while True:
imageResp = urlopen(url)
imageNp = np.array(bytearray(imageResp.read()), dtype=np.uint8)
frame = cv2.imdecode(imageNp, -1)
# Convert frame to grayscale
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# Detect multi faces in the image
faces = face_cascade.detectMultiScale(gray, 1.3, 5)
for face in faces:
x, y, w, h = face
# Get the face ROI
offset = 7
face_section = frame[y-offset:y+h+offset, x-offset:x+w+offset]
face_section = cv2.resize(face_section, (100, 100))
out = knn(trainset, face_section.flatten())
# Draw rectangle in the original image
cv2.putText(frame, names[int(out)],(x,y-10), font, 1,(255,0,0),2, lineType = cv2.CV_AA)
cv2.rectangle(frame, (x,y), (x+w,y+h), (0,255,0), 2)
cv2.imshow("Faces", frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cv2.destroyAllWindows()
import pandas as pd
from DMC import dmc
from KNN import knn
from NN import nn
data = pd.read_csv("iris.csv")
testSet = [[7.2, 3.6, 5.1, 2.5]]
test = pd.DataFrame(testSet)
k = 5
result1, neighbor1 = nn(data, test)
result2, neighbor2 = knn(data, test, k)
result3, neighbor3 = dmc(data, test)
print("\nResultados: ")
print("NN\n\tResults: {} - Vizinho: {}".format(result1, neighbor1))
print("KNN\n\tResults: {} - Vizinho: {}".format(result2, neighbor2))
print("DMC\n\tResults: {} - Vizinho(Centroide): {}".format(result3, neighbor3))