Machine Learning and algorithm

K Nearest NeighborGridSearchCV Linear regressionLinearRegressionSGDRegressorRegularized linear modelRidge RegressionLosso Regression Logistic RegressionDecisionTreeBoosting & BaggingKmeansOthersfeature extractionCountVectorizer Feature dimensionality reductionPCACorrelated Features the guidance of choosing algorithm

K Nearest Neighbor

import pandas as pd import numpy as np from sklearn.neighbors import KNeighborsClassifier # classifier from sklearn.preprocessing import StandardScaler # standard from sklearn.model_selection import train_test_split #split data #read data data=pd.read_csv('data/---.csv') data.head() # feature,score x=data[['--','---','---']] #array_x should be two-dimensional y=data[['target--']] #score # split data x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.3,random_state=24) #test_size-the test data ratio。random_state---set casually，migrate easily # standard sc=StandardScaler() new_x_train=sc.fit_transform(x_train) new_x_test=sc.transform(x_test) # machine learning knn=KNeighborsClassifier() knn.fit(new_x_train,y_train) #model training knn.predict(new_x_test) #model prediction knn.score(new_x_test,y_test) #model assessment

GridSearchCV

gridsearch and cross validation

import pandas as pd import numpy as np from sklearn.neighbors import KNeighborsClassifier # classifier from sklearn.preprocessing import StandardScaler # standard from sklearn.model_selection import train_test_split,GridSearchCV #split data and gridsearchcv # read data data=pd.read_csv('data/---.csv') data.head() # feature,score x=data[['--','---','---']] #array_x should be two-dimensional y=data[['target--']] #score # split data x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.3,random_state=24) #test_size-the test data ratio。random_state---set casually，migrate easily # standard sc=StandardScaler() new_x_train=sc.fit_transform(x_train) new_x_test=sc.transform(x_test) # mahine learning------ knn=KNeighborsClassifier() # GridSearchCv-----------------------! param_dict={'n_neighbors':[1,3,5]} # param dict for adjustment es=GridSearchCV(knn,param_grid=param_dict,cv=3) # gridsearch and cross validation es.fit(new_x_train,y_train) #data training # model assessment y_predict=es.predict(x_test) # predict y score=es.score(x_test,y_test) # calculate the precision es.best_score_ # best score es.best_params_ # best params

Linear regression

LinearRegression

from sklearn.linear_model import LinearRegression from sklearn.metrics import mean_squared_error ......... #model training lr=LinearRegression() lr.fit(new_x_train,y_train) #prediction y_pred=lr.predict(new_x_test) print("y_prediction:",y_pred) lr.coef_ #w # coef_array of shape (n_features, ) or (n_targets, n_features) --->can be regarded as '系数' lr.intercept_ #b # intercept_float or array of shape (n_targets,)----->can be regarded as '截距' #model assessment err=mean_squared_error(y_test,y_pred) err

SGDRegressor

Stochastic gradient descent from sklearn.linear_model import SGDRegressor from sklearn.metrics import mean_squared_error ......... # model training lr2=SGDRegressor(max_iter=5000,learning_rate='constant',eta0=0.001) lr2.fit(new_x_train,y_train) #prediction y_pred=lr.predict(new_x_test) print("y_prediction:",y_pred) # model assessment score=lr.score(new_x_test,y_test)#[0,1] be better to close "1" print(score) error=predictions-y_test#calculate error rmse=(error**2).mean()**.5#calculate rmse mae=abs(error).mean()#calculatemae print(rmse) print(mae)

Regularized linear model

Ridge Regression

sklearn.linear_model.Ridge(alpha=1.0, fit_intercept=True,solver=“auto”, normalize=False)

# ridge=Ridge(alpha=0.1) ridge=RidgeCV(alphas=(0.001,0.005,0.1,0.5,1,10,20,50,100)) ridge.fit(new_x_train,y_train) #predict y_pred=ridge.predict(new_x_test)

Losso Regression

Logistic Regression

sklearn.linear_model.LogisticRegression(solver=‘liblinear’, penalty=‘l2’, C = 1.0)

#model training lr=LogisticRegression() lr.fit(new_x_train,y_train) #model assessment pred=lr.predict(new_x_test) pred #ouput score lr.score(new_x_test,y_test) # the distribution of test data y_test.value_counts() # assessment from sklearn.metrics import confusion_matrix confusion_matrix(y_test,pred) tn,fp,fn,tp=confusion_matrix(y_test,pred).ravel() tn,fp,fn,tp pr=tp/(tp+fp) # precision recall=tp/(tp+fn) # recall #api for calculating precision and recall from sklearn.metrics import precision_score,recall_score precision_score(y_true,y_pred) # y_true and y_pred must be 1 or 0 recall_score(y_true,y_pred) #calculate f1 f1=2*tp/(2*tp+fn+fp) f1 f12=2*pr*recall/(pr+recall) f12 # f1_score from sklearn.metrics import f1_score f1_score(y_true,y_pred) # classification_report!!!!!!!!!!! from sklearn.metrics import classification_report print(classification_report(y_test,pred,labels=(1,0),target_names=("good","bad"))) precision_score(y_true,y_pred)

DecisionTree

import pandas as pd import numpy as np from sklearn.feature_extration import DictVectorizer # transform non-numeric data into numerical value----onehot from sklearn.model_selection import train_test_split from sklearn.tree import DecisionTreeClassifier,export_graphviz data=pd.read_csv('data/----.csv') x=data[['--','--','--','--']] y=data['--'] # solve the null x['--'].fillna(x['--'].mean(),inplace=True) x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.3,random_state=12) # split data # feature extraction # DictVectorizer can only deal with the "dict",must use 'to_dict' to make that transfer=DictVectorizer(sparse=False) x_train=transfer.fit_transform(x_train.to_dict(orient="records")) x_test=transfer.transform(x_test.to_dict(orient='records')) # machine learning es=DecisionTreeClassfier(criterion="entropy", max_depth=5) es.fit(x_train,y_train) es.score(x_test,y_test) es.predict(x_test) tree.export_graphviz(estimator,out_file='tree.dot’,feature_names=[‘’,’’]) # the visualization of decision tree

Boosting & Bagging

RandomForest

from sklearn.ensemble import RandomForestClassifier from sklearn.model_selection import GridSearchCV # init the object rf=RandomForestClassifier() # setting the param= {"n_estimators": [120,200,300,500,800,1200], "max_depth": [5, 8, 15, 25, 30]} # define gridsearch gs=GridSearchCV(rf,param_grid=param,cv=3) gs.fit(new_x_train,y_train) gs.score(new_x_test,y_test) gs.best_params_

adaboost

from sklearn.ensemble import AdaBoostClassifier ada=AdaBoostClassifier(n_estimators=1000,learning_rate=0.01) ada.fit(new_x_train,y_train) ada.score(new_x_test,y_test)

Kmeans

from sklearn.cluster import KMeans from sklearn.metrics import silhouette_score # model training km=KMeans(n_clusters=8,random_state=24) km.fit(data) y_predict=km.predict(data) km.cluster_centers_ silhouette_score(data, y_predict)

Others

feature extraction

CountVectorizer

# from sklearn.feature_extraction.text import CountVectorizer # get data data=["人生苦短，我喜欢Python","生活太长久，我不喜欢Python"] stop_words={'。','，'} # init the object vector=CountVectorizer(tokenizer=jieba.lcut,stop_words=stop_words) new_data=vector.fit_transform(data)# handle the data print(new_data.toarray())# # into dataFrame pd.DataFrame(new_data.toarray(),columns=vector.get_feature_names()).T

Feature dimensionality reduction

Feature selector that removes all low-variance features.

from sklearn.feature_selection import VarianceThreshold # removes all low-variance features vt=VarianceThreshold(threshold=1) new_x=vt.fit_transform(x) new_x.shape

PCA

Principal component analysis (PCA).

from sklearn.decomposition import PCA pca=PCA(n_components=2) pca_x=pca.fit_transform(new_x) pca_x.shape

Correlated Features

# pearsonr from scipy.stats import pearsonr x1 = [12.5, 15.3, 23.2, 26.4, 33.5, 34.4, 39.4, 45.2, 55.4, 60.9] x2 = [21.2, 23.9, 32.9, 34.1, 42.5, 43.2, 49.0, 52.8, 59.4, 63.5] pearsonr(x1,x2) # spearmanr from scipy.stats import spearmanr spearmanr(x1,x2)

the guidance of choosing algorithm