常用机器学习算法的python实现

KNN

参数指定版

from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
import pandas as pd 
 #read data
data = pd.read_csv('D:/column_2C_weka.csv')
 #n_neighbors: K. In this example it is 3. it means that Look at the 3 closest labeled data points
knn = KNeighborsClassifier(n_neighbors = 3)  
  #x: features y: target variables
x,y = data.loc[:,data.columns != 'class'], data.loc[:,'class']   
 #split our data train and test sets
x_train,x_test,y_train,y_test = train_test_split(x,y,test_size = 0.3,random_state = 1)
knn.fit(x_train,y_train)   #train the data
prediction = knn.predict(x_test) #predicts the data 
print('Prediction: {}'.format(prediction))
print('With KNN (K=3) accuracy is: ',knn.score(x_test,y_test)) # accuracy

调参版,其他算法的调参均可参照于此

from sklearn.model_selection import GridSearchCV
grid = {'n_neighbors': np.arange(1,50)}
knn = KNeighborsClassifier()
knn_cv = GridSearchCV(knn, grid, cv=3) # GridSearchCV
knn_cv.fit(x,y)# Fit

# Print hyperparameter
print("Tuned hyperparameter k: {}".format(knn_cv.best_params_)) 
print("Best score: {}".format(knn_cv.best_score_))

数据切分

将数据集划分为训练集与测试集

 # train/test split
from sklearn.model_selection import train_test_split
x,y = data.loc[:,data.columns != 'class'], data.loc[:,'class']
 #test_size:percentage of test size, train_size = 1 - test_size
 #random_state: sets a seed. If this seed is same number, 
 #train_test_split() produce exact same split at each time
x_train,x_test,y_train,y_test = train_test_split(x,y,test_size =\ 0.3,random_state = 1)
knn = KNeighborsClassifier(n_neighbors = 3)
 #train with train_set
knn.fit(x_train,y_train)
 #predict with test_set
prediction = knn.predict(x_test)
print('With KNN (K=3) accuracy is: ',knn.score(x_test,y_test)) # accuracy

LR-线性回归

from sklearn.metrics import roc_curve
from sklearn.metrics import confusion_matrix, classification_report
# LinearRegression
from sklearn.linear_model import LinearRegression
reg = LinearRegression()
# Predict space
predict_space = np.linspace(min(x), max(x)).reshape(-1,1)
# Fit
reg.fit(x,y)
# Predict
predicted = reg.predict(predict_space)
# R^2 
print('R^2 score: ',reg.score(x, y))

y_pred_prob = reg.predict_proba(x_test)[:,1]\
fpr, tpr, thresholds = roc_curve(y_test, y_pred_prob)
# Plot ROC curve
plt.plot([0, 1], [0, 1], 'k--')
plt.plot(fpr, tpr)
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('ROC')
plt.show()

K fold CROSS VALIDATION-k fold CV-K折交叉验证

参数指定版

from sklearn.model_selection import cross_val_score
reg = LinearRegression()
k = 5 
cv_result = cross_val_score(reg,x,y,cv=k) # uses R^2 as score
print('CV Scores: ',cv_result)
print('CV scores average: ',np.sum(cv_result)/k)

调参版

# grid search cross validation with 2 hyperparameter
# 1. hyperparameter is C:logistic regression regularization parameter
# 2. penalty l1 or l2
# Hyperparameter grid
param_grid = {'C': np.logspace(-3, 3, 7), 'penalty': ['l1', 'l2']}
x_train, x_test, y_train, y_test = train_test_split(x,y,\
test_size = 0.3,random_state = 12)
logreg = LogisticRegression()
logreg_cv = GridSearchCV(logreg,param_grid,cv=3)
logreg_cv.fit(x_train,y_train)

# Print the optimal parameters and best score
print("Tuned hyperparameters : {}".format(logreg_cv.best_params_))
print("Best Accuracy: {}".format(logreg_cv.best_score_))

CROSS VALIDATION-正则化回归

损失函数正则化，分别采用L2和L1正则化

# Ridge-L2
from sklearn.linear_model import Ridge
x_train,x_test,y_train,y_test = train_test_split(x,y,random_state = 2,\ test_size = 0.3)
# alpha-正则化项的系数
ridge = Ridge(alpha = 0.1, normalize = True)
ridge.fit(x_train,y_train)
ridge_predict = ridge.predict(x_test)
print('Ridge score: ',ridge.score(x_test,y_test))

# Lasso-L1
from sklearn.linear_model import Lasso
x = np.array(data1.loc[:,['pelvic_incidence','pelvic_tilt numeric',
'lumbar_lordosis_angle','pelvic_radius']])
x_train,x_test,y_train,y_test = train_test_split(x,y,random_state = 3,\ test_size = 0.3)
lasso = Lasso(alpha = 0.1, normalize = True)
lasso.fit(x_train,y_train)
ridge_predict = lasso.predict(x_test)
print('Lasso score: ',lasso.score(x_test,y_test))
print('Lasso coefficients: ',lasso.coef_)

Random forest

# Confusion matrix with random forest
from sklearn.metrics import classification_report, confusion_matrix
from sklearn.ensemble import RandomForestClassifier
x,y = data.loc[:,data.columns != 'class'], data.loc[:,'class']
x_train,x_test,y_train,y_test = train_test_split(x,y,test_size = 0.3,\
random_state = 1)
rf = RandomForestClassifier(random_state = 4)
rf.fit(x_train,y_train)
y_pred = rf.predict(x_test)
cm = confusion_matrix(y_test,y_pred)
print('Confusion matrix: \n',cm)
print('Classification report: \n',classification_report(y_test,y_pred))

K-means

#STANDARDIZATION
data3 = data.drop('class',axis = 1)
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import make_pipeline
scalar = StandardScaler()
kmeans = KMeans(n_clusters = 2)
pipe = make_pipeline(scalar,kmeans)
pipe.fit(data3)
labels = pipe.predict(data3)
df = pd.DataFrame({'labels':labels,"class":data['class']})
ct = pd.crosstab(df['labels'],df['class'])
print(ct)

T - Distributed Stochastic Neighbor Embedding (T - SNE)1.

from sklearn.manifold import TSNE
model = TSNE(learning_rate=100)
transformed = model.fit_transform(data2)
x = transformed[:,0]
y = transformed[:,1]
plt.scatter(x,y,c = color_list )
plt.xlabel('pelvic_radius')
plt.xlabel('degree_spondylolisthesis')
plt.show()

---

1. http://www.datakit.cn/blog/2017/02/05/t_sne_full.html ↩