def run_main():
file_df = pd.read_csv('../dataset/voice.csv')
# print file_df
insect_dataset(file_df)
#填充空数据
drop_na(file_df)
#查看label的个数 分组显示
# print file_df['label'].value_counts()
#特征分布可视化
fea_name1 = 'meanfun'
fea_name2 = 'centroid'
#两个属性的特征图
# visaulize_two_feature(file_df,fea_name1,fea_name2)
#艺术性属性的特征图
# visaulize_single_feature(file_df,fea_name1)
#多个特征
fea_name = ['meanfreq', 'Q25', 'Q75', 'skew', 'centroid', 'label']
# visaulize_muilt_feature(file_df,fea_name)
X = file_df.iloc[:, :-1].values
file_df['label'].replace('male', 0, inplace=True)
file_df['label'].replace('female', 1, inplace=True)
y = file_df['label'].values
#特征归一化
X = preprocessing.scale(X)
#分割训练集，测试集
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=1 / 3.,
random_state=5)
#选择模型 交叉验证
cv_scores = []
k_range = range(1, 31)
for k in k_range:
knn = KNeighborsClassifier(k)
# print 'knn:',knn
scores = cross_val_score(knn,
X_train,
y_train,
cv=10,
scoring='accuracy')
score_mean = scores.mean()
cv_scores.append(score_mean)
print '%i:%.4f' % (k, score_mean)
best_k = np.argmax(cv_scores) + 1
#训练模型
knn_model = KNeighborsClassifier(best_k)
knn_model.fit(X_train, y_train)
print '测试模型，准确率：', knn_model.score(X_test, y_test)
return ''
def get_best_k(X, y, max_k=30, keep_best_n=10, weights=None):
# TODO: check X, y. description
# Set default values
if max_k is None:
max_k = len(X)
if weights is None:
weights = ['uniform', 'distance']
# Make weights into a list if it is not already one
if type(weights) is not list:
weights = [weights]
# Check if inputs are valid
check_pandas_dataframe_nd(X, 'X')
check_numpy_array_pandas_dataframe_series_1d(y, 'y')
check_list_of_strings(weights, 'weights')
check_integer(max_k, 'max_k')
check_larger(max_k, 'max_k', 1)
check_integer(keep_best_n, 'keep_best_n')
check_larger(keep_best_n, 'keep_best_n', 1)
# Change shape of y if necessary
y = np.array(y)
y = y.ravel()
# Split into train and test data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
# Get value for max_k
max_k = min(max_k, len(X_test))
# Set up results-list
best_model = []
for k in range(1, max_k):
for weight in weights:
model = KNeighborsClassifier(n_neighbors=k,
weights=weight).fit(X_train, y_train)
score = model.score(X_test, y_test)
best_model.append((k, weight, score))
best_model.sort(key=lambda x: x[2], reverse=True)
best_model = best_model[0:keep_best_n]
return best_model
import matplotlib.pyplot as plt
import mglearn
cancer = load_breast_cancer()
#print(cancer.data) # X : data
#print(cancer.target_names) # y : label
X_train, X_test, y_train, y_test = train_test_split(cancer.data, cancer.target,
stratify = cancer.target, random_state=66)
training_accuracy = []
test_accuracy = []
# 1 ~ 10까지 n_neighbors를 적용
neighbors_setting = range(1,11)
for n_neighbors in neighbors_setting:
# 모델 생성
clf = KNeighborsClassifier(n_neighbors= n_neighbors)
clf.fit(X_train, y_train)
# train 세트 정확도 저장
training_accuracy.append(clf.score(X_train, y_train))
# 일반화 정확도 저장
test_accuracy.append(clf.score(X_test, y_test))
plt.plot(neighbors_setting, training_accuracy, label='traing accuracy')
plt.plot(neighbors_setting, test_accuracy, label='test accuracy')
plt.ylabel('Accuracy')
plt.xlabel('n_neighbors')
plt.legend()
plt.show()
