def main(filename):
# dataset, indexes = data_handler.get_data(filename)
trainX, trainY, testX, testY = data_handler.splitData2TestTrain(
data_handler.pickDataClass(
'Handwrittenletters.txt',
data_handler.letter_2_digit_convert("ABCDEFGHIJ")), 39, "1:20")
predict(trainX, trainY, testX, testY, 4)
def driver(classifier):
print (getTitle(classifier))
if classifier == 4:
trainX, trainY, testX, testY = data_handler.splitData2TestTrain('ATNTFaceImages400.txt', 10, '1:10')
print ("\nAverage Accuracy for 5 folds: %s"% SVM.cross_validate(trainX, trainY, testX, testY))
else:
data, indexes = data_handler.get_data("ATNTFaceImages400.txt")
print ("\nAverage Accuracy for 5 folds: %s"%cross_validator(5, data, indexes, classifier))
def driver():
for i in range(1, data_frame.shape[1]):
compute_f_test(data_frame.iloc[:, [0, i]], i)
f_data_des = np.array(sorted(f_data, key=itemgetter(1), reverse=True))
top_selected_samples = f_data_des[:100, :]
top_100_ixs = top_selected_samples.astype('int')
print ("Selected top %s sample indexes and f_scores \n"%len(top_selected_samples))
for index, item in enumerate(top_selected_samples):
print ("%s => %s - %s"%(index+1, item[0], item[1]))
top_100_ixs = np.insert(top_100_ixs, 0, 0)
training_data = data_frame.iloc[:, top_100_ixs]
train_x, train_y, testX, testY = data_handler.splitData2TestTrain(training_data.as_matrix().tolist(), 39, "20:19")
print ("\nPredicted Classes : \n")
classify_and_predict(SVC(kernel='linear'), train_x, train_y, testX)
import data_handler
import LinearRegression
import centroid_classifier
import kn_classifier
import SVM
dataset_file = "Handwrittenletters.txt"
test_string = "DCIAYNKR" #4391 YVKR
test_instances = "1:10"
instances_pre_class = 39
trainX, trainY, testX, testY = data_handler.splitData2TestTrain(\
data_handler.pickDataClass(\
dataset_file,
data_handler.letter_2_digit_convert(\
test_string)),
instances_pre_class,
test_instances)
data_handler.store_data(trainX, trainY, testX, testY)
print ("Actual classes %s"%data_handler.letter_2_digit_convert(test_string))
print ("Centroid method")
centroid_acc, prediction = centroid_classifier.predict(trainX, trainY, testX, testY, 3)
print ("Centroid accuracy %s"%centroid_acc)
print ("Predicted Classes %s"%prediction)
print ("============================================================================")
print ("KNN method")
kn_acc, prediction = kn_classifier.knn_driver(trainX, testX, 3)
print ("KNN accuracy %s"%kn_acc)
print ("Predicted Classes %s"%prediction)
from numpy import vstack,array, int32
from numpy.random import rand
# from scipy.cluster.vq import kmeans,vq
from sklearn.cluster import KMeans
import pandas as pd
from sklearn.metrics import confusion_matrix
import matplotlib.pyplot as plt
import Hungarian_python
import data_handler
filename = "HandWrittenLetters.txt"
number_per_class = 39
test_instances = "1:3"
nu_clusters = 26
trainX, trainY, testX, testY = data_handler.splitData2TestTrain(filename, number_per_class, test_instances)
# trainX, trainY, testX, testY = data_handler.splitData2TestTrain(data_handler.pickDataClass(filename, ['1', '2', '3', '4']), 10, "1:3")
trainX.extend(testX)
trainX = array(trainX, int32)
testX = array(testX, int32)
# colors = ["g.","r.","c.","y.", "w.", "b.", "a.", "e.", "f.", "h."]
kmeans = KMeans (n_clusters=nu_clusters)
kmeans.fit(trainX)
centroids = kmeans.cluster_centers_
labels = kmeans.labels_
# for i in range(len(trainX)):
# print("coordinate:",trainX[i], "label:", labels[i])
import data_handler
import matplotlib as mpl
mpl.use('TkAgg')
import matplotlib.pyplot as plt
import Task1
all_accs = []
sample_string = "adgjwryozm"
splits = ["1:34", "1:29", "1:24", "1:19", "1:14", "1:9", "1:4"]
for split in splits:
print("Current split %s" % split)
trainX, trainY, testX, testY = data_handler.splitData2TestTrain(
data_handler.pickDataClass(
'Handwrittenletters.txt',
data_handler.letter_2_digit_convert(sample_string)), 39, split)
all_accs.append(Task1.predict(trainX, trainY, testX, testY, 10))
print(all_accs)
x = [1, 2, 3, 4, 5, 6, 7]
# Plot the data
for i in range(len(x)):
plt.scatter(x[i], all_accs[i], color='black', marker='^')
plt.plot(x[i], all_accs[i], label=i)
plt.legend(loc='lower right', frameon=False)
# Show the plot
plt.show()
mpl.use('TkAgg')
import matplotlib.pyplot as plt
from sklearn.neighbors import KNeighborsClassifier
from sklearn.neighbors.nearest_centroid import NearestCentroid
from sklearn.linear_model import LinearRegression
from sklearn import linear_model
from sklearn import svm
from sklearn import metrics
import math
import operator
import data_handler
data = pd.read_csv('HandWrittenLetters.txt', header=-1).as_matrix()
trainX, trainY, testX, testY = data_handler.splitData2TestTrain(
data_handler.pickDataClass('Handwrittenletters.txt',
data_handler.letter_2_digit_convert("abcde")),
39, "1:9")
def getCentroid(labelVectors):
curr_centroid = []
for j in range(len(labelVectors[0]) - 1):
curr_sum = 0
for i in range(len(labelVectors)):
curr_sum += int(labelVectors[i][j])
curr_sum = float(curr_sum) / len(labelVectors)
curr_centroid.append(curr_sum)
curr_centroid.append(labelVectors[-1][-1])
return curr_centroid