\n
import pandas as pd from sklearn.model_selection import cross_val_score, StratifiedKFold, GridSearchCV from sklearn.metrics import accuracy_score # \u0417\u0430\u0433\u0440\u0443\u0436\u0430\u0435\u043c \u0434\u0430\u043d\u043d\u044b\u0435 df = pd.read_csv("..\/..\/data\/telecom_churn.csv") # \u0412\u044b\u0431\u0438\u0440\u0430\u0435\u043c \u0441\u043d\u0430\u0447\u0430\u043b\u0430 \u0442\u043e\u043b\u044c\u043a\u043e \u043a\u043e\u043b\u043e\u043d\u043a\u0438 \u0441 \u0447\u0438\u0441\u043b\u043e\u0432\u044b\u043c \u0442\u0438\u043f\u043e\u043c \u0434\u0430\u043d\u043d\u044b\u0445 cols = [] for i in df.columns: if (df[i].dtype == "float64") or (df[i].dtype == 'int64'): cols.append(i) # \u0420\u0430\u0437\u0434\u0435\u043b\u044f\u0435\u043c \u043d\u0430 \u043f\u0440\u0438\u0437\u043d\u0430\u043a\u0438 \u0438 \u043e\u0431\u044a\u0435\u043a\u0442\u044b X, y = df[cols].copy(), np.asarray(df["Churn"],dtype='int8') # \u0418\u043d\u0438\u0446\u0438\u0430\u043b\u0438\u0437\u0438\u0440\u0443\u0435\u043c \u0441\u0442\u0440\u0430\u0438\u0444\u0438\u0446\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u0443\u044e \u0440\u0430\u0437\u0431\u0438\u0432\u043a\u0443 \u043d\u0430\u0448\u0435\u0433\u043e \u0434\u0430\u0442\u0430\u0441\u0435\u0442\u0430 \u0434\u043b\u044f \u0432\u0430\u043b\u0438\u0434\u0430\u0446\u0438\u0438 skf = StratifiedKFold(n_splits=5, shuffle=True, random_state=42) # \u0418\u043d\u0438\u0446\u0438\u0430\u043b\u0438\u0437\u0438\u0440\u0443\u0435\u043c \u043d\u0430\u0448 \u043a\u043b\u0430\u0441\u0441\u0438\u0444\u0438\u043a\u0430\u0442\u043e\u0440 \u0441 \u0434\u0435\u0444\u043e\u043b\u0442\u043d\u044b\u043c\u0438 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u0430\u043c\u0438 rfc = RandomForestClassifier(random_state=42, n_jobs=-1, oob_score=True) # \u041e\u0431\u0443\u0447\u0430\u0435\u043c \u043d\u0430 \u0442\u0440\u0435\u043d\u0438\u0440\u043e\u0432\u043e\u0447\u043d\u043e\u043c \u0434\u0430\u0442\u0430\u0441\u0435\u0442\u0435 results = cross_val_score(rfc, X, y, cv=skf) # \u041e\u0446\u0435\u043d\u0438\u0432\u0430\u0435\u043c \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u044c \u043d\u0430 \u0442\u0435\u0441\u0442\u043e\u0432\u043e\u043c \u0434\u0430\u0442\u0430\u0441\u0435\u0442\u0435 print("CV accuracy score: {:.2f}%".format(results.mean()*100))<\/code><\/pre>\n<\/div>\n<\/div>\n <\/p>\n
\u041f\u043e\u043b\u0443\u0447\u0438\u043b\u0438 \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u044c 91.21%, \u0442\u0435\u043f\u0435\u0440\u044c \u043f\u043e\u043f\u0440\u043e\u0431\u0443\u0435\u043c \u0443\u043b\u0443\u0447\u0448\u0438\u0442\u044c \u044d\u0442\u043e\u0442 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442 \u0438 \u043f\u043e\u0441\u043c\u043e\u0442\u0440\u0435\u0442\u044c, \u043a\u0430\u043a \u0432\u0435\u0434\u0443\u0442 \u0441\u0435\u0431\u044f \u043a\u0440\u0438\u0432\u044b\u0435 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u043f\u0440\u0438 \u0438\u0437\u043c\u0435\u043d\u0435\u043d\u0438\u0438 \u043e\u0441\u043d\u043e\u0432\u043d\u044b\u0445 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432.<\/p>\n
<\/p>\n
\u041d\u0430\u0447\u043d\u0435\u043c \u0441 \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u0430 \u0434\u0435\u0440\u0435\u0432\u044c\u0435\u0432:<\/p>\n
<\/p>\n
\u041a\u043e\u0434 \u0434\u043b\u044f \u043f\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u044f \u043a\u0440\u0438\u0432\u044b\u0445 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u043f\u043e \u043f\u043e\u0434\u0431\u043e\u0440\u0443 \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u0430 \u0434\u0435\u0440\u0435\u0432\u044c\u0435\u0432<\/b><\/p>\n\n
# \u0418\u043d\u0438\u0446\u0438\u0430\u043b\u0438\u0437\u0438\u0440\u0443\u0435\u043c \u0432\u0430\u043b\u0438\u0434\u0430\u0446\u0438\u044e skf = StratifiedKFold(n_splits=5, shuffle=True, random_state=42) # \u0421\u043e\u0437\u0434\u0430\u0435\u043c \u0441\u043f\u0438\u0441\u043a\u0438 \u0434\u043b\u044f \u0441\u043e\u0445\u0440\u0430\u043d\u0435\u043d\u0438\u044f \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u0438 \u043d\u0430 \u0442\u0440\u0435\u043d\u0438\u0440\u043e\u0432\u043e\u0447\u043d\u043e\u043c \u0438 \u0442\u0435\u0441\u0442\u043e\u0432\u043e\u043c \u0434\u0430\u0442\u0430\u0441\u0435\u0442\u0435 train_acc = [] test_acc = [] temp_train_acc = [] temp_test_acc = [] trees_grid = [5, 10, 15, 20, 30, 50, 75, 100] # \u041e\u0431\u0443\u0447\u0430\u0435\u043c \u043d\u0430 \u0442\u0440\u0435\u043d\u0438\u0440\u043e\u0432\u043e\u0447\u043d\u043e\u043c \u0434\u0430\u0442\u0430\u0441\u0435\u0442\u0435 for ntrees in trees_grid: rfc = RandomForestClassifier(n_estimators=ntrees, random_state=42, n_jobs=-1, oob_score=True) temp_train_acc = [] temp_test_acc = [] for train_index, test_index in skf.split(X, y): X_train, X_test = X.iloc[train_index], X.iloc[test_index] y_train, y_test = y[train_index], y[test_index] rfc.fit(X_train, y_train) temp_train_acc.append(rfc.score(X_train, y_train)) temp_test_acc.append(rfc.score(X_test, y_test)) train_acc.append(temp_train_acc) test_acc.append(temp_test_acc) train_acc, test_acc = np.asarray(train_acc), np.asarray(test_acc) print("Best accuracy on CV is {:.2f}% with {} trees".format(max(test_acc.mean(axis=1))*100, trees_grid[np.argmax(test_acc.mean(axis=1))]))<\/code><\/pre>\n<\/div>\n<\/div>\n <\/p>\n
\u041a\u043e\u0434 \u0434\u043b\u044f \u043f\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u044f \u0433\u0440\u0430\u0444\u0438\u043a\u0430 \u043a\u0440\u0438\u0432\u044b\u0445 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f<\/b><\/p>\n\n
import matplotlib.pyplot as plt plt.style.use('ggplot') %matplotlib inline fig, ax = plt.subplots(figsize=(8, 4)) ax.plot(trees_grid, train_acc.mean(axis=1), alpha=0.5, color='blue', label='train') ax.plot(trees_grid, test_acc.mean(axis=1), alpha=0.5, color='red', label='cv') ax.fill_between(trees_grid, test_acc.mean(axis=1) - test_acc.std(axis=1), test_acc.mean(axis=1) + test_acc.std(axis=1), color='#888888', alpha=0.4) ax.fill_between(trees_grid, test_acc.mean(axis=1) - 2*test_acc.std(axis=1), test_acc.mean(axis=1) + 2*test_acc.std(axis=1), color='#888888', alpha=0.2) ax.legend(loc='best') ax.set_ylim([0.88,1.02]) ax.set_ylabel("Accuracy") ax.set_xlabel("N_estimators")<\/code><\/pre>\n<\/div>\n<\/div>\n <\/p>\n
![\"image\"\/](\"https:\/\/github.com\/Yorko\/mlcourse_open\/blob\/master\/img\/rf_n_est.png?raw=true\")
<\/p>\n
<\/p>\n
\u041a\u0430\u043a \u0432\u0438\u0434\u043d\u043e, \u043f\u0440\u0438 \u0434\u043e\u0441\u0442\u0438\u0436\u0435\u043d\u0438\u0438 \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u043d\u043e\u0433\u043e \u0447\u0438\u0441\u043b\u0430 \u0434\u0435\u0440\u0435\u0432\u044c\u0435\u0432, \u043d\u0430\u0448\u0430 \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u044c \u043d\u0430 \u0442\u0435\u0441\u0442\u0435 \u0432\u044b\u0445\u043e\u0434\u0438\u0442 \u043d\u0430 \u0430\u0441\u0438\u043c\u043f\u0442\u043e\u0442\u0443, \u0438 \u0432\u044b \u043c\u043e\u0436\u0435\u0442\u0435 \u0441\u0430\u043c\u0438 \u0440\u0435\u0448\u0438\u0442\u044c, \u0441\u043a\u043e\u043b\u044c\u043a\u043e \u0434\u0435\u0440\u0435\u0432\u044c\u0435\u0432 \u043e\u043f\u0442\u0438\u043c\u0430\u043b\u044c\u043d\u043e \u0434\u043b\u044f \u0432\u0430\u0448\u0435\u0439 \u0437\u0430\u0434\u0430\u0447\u0438.
\u041d\u0430 \u0440\u0438\u0441\u0443\u043d\u043a\u0435 \u0442\u0430\u043a\u0436\u0435 \u0432\u0438\u0434\u043d\u043e, \u0447\u0442\u043e \u043d\u0430 \u0442\u0440\u0435\u043d\u0438\u0440\u043e\u0432\u043e\u0447\u043d\u043e\u0439 \u0432\u044b\u0431\u043e\u0440\u043a\u0435 \u043c\u044b \u0441\u043c\u043e\u0433\u043b\u0438 \u0434\u043e\u0441\u0442\u0438\u0447\u044c 100% \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u0438, \u044d\u0442\u043e \u0433\u043e\u0432\u043e\u0440\u0438\u0442 \u043d\u0430\u043c \u043e \u043f\u0435\u0440\u0435\u043e\u0431\u0443\u0447\u0435\u043d\u0438\u0438 \u043d\u0430\u0448\u0435\u0439 \u043c\u043e\u0434\u0435\u043b\u0438. \u0427\u0442\u043e\u0431\u044b \u0438\u0437\u0431\u0435\u0436\u0430\u0442\u044c \u043f\u0435\u0440\u0435\u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f, \u043c\u044b \u0434\u043e\u043b\u0436\u043d\u044b \u0434\u043e\u0431\u0430\u0432\u0438\u0442\u044c \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u044b \u0440\u0435\u0433\u0443\u043b\u044f\u0440\u0438\u0437\u0430\u0446\u0438\u0438 \u0432 \u043c\u043e\u0434\u0435\u043b\u044c.<\/p>\n
<\/p>\n
\u041d\u0430\u0447\u043d\u0435\u043c \u0441 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u0430 \u043c\u0430\u043a\u0441\u0438\u043c\u0430\u043b\u044c\u043d\u043e\u0439 \u0433\u043b\u0443\u0431\u0438\u043d\u044b \u2013 max_depth<\/code>. (\u0437\u0430\u0444\u0438\u043a\u0441\u0438\u0440\u0443\u0435\u043c \u043a-\u0432\u043e \u0434\u0435\u0440\u0435\u0432\u044c\u0435\u0432 100)<\/p>\n <\/p>\n
\u041a\u043e\u0434 \u0434\u043b\u044f \u043f\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u044f \u043a\u0440\u0438\u0432\u044b\u0445 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u043f\u043e \u043f\u043e\u0434\u0431\u043e\u0440\u0443 \u043c\u0430\u043a\u0441\u0438\u043c\u0430\u043b\u044c\u043d\u043e\u0439 \u0433\u043b\u0443\u0431\u0438\u043d\u044b \u0434\u0435\u0440\u0435\u0432\u0430<\/b><\/p>\n\n
# \u0421\u043e\u0437\u0434\u0430\u0435\u043c \u0441\u043f\u0438\u0441\u043a\u0438 \u0434\u043b\u044f \u0441\u043e\u0445\u0440\u0430\u043d\u0435\u043d\u0438\u044f \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u0438 \u043d\u0430 \u0442\u0440\u0435\u043d\u0438\u0440\u043e\u0432\u043e\u0447\u043d\u043e\u043c \u0438 \u0442\u0435\u0441\u0442\u043e\u0432\u043e\u043c \u0434\u0430\u0442\u0430\u0441\u0435\u0442\u0435 train_acc = [] test_acc = [] temp_train_acc = [] temp_test_acc = [] max_depth_grid = [3, 5, 7, 9, 11, 13, 15, 17, 20, 22, 24] # \u041e\u0431\u0443\u0447\u0430\u0435\u043c \u043d\u0430 \u0442\u0440\u0435\u043d\u0438\u0440\u043e\u0432\u043e\u0447\u043d\u043e\u043c \u0434\u0430\u0442\u0430\u0441\u0435\u0442\u0435 for max_depth in max_depth_grid: rfc = RandomForestClassifier(n_estimators=100, random_state=42, n_jobs=-1, oob_score=True, max_depth=max_depth) temp_train_acc = [] temp_test_acc = [] for train_index, test_index in skf.split(X, y): X_train, X_test = X.iloc[train_index], X.iloc[test_index] y_train, y_test = y[train_index], y[test_index] rfc.fit(X_train, y_train) temp_train_acc.append(rfc.score(X_train, y_train)) temp_test_acc.append(rfc.score(X_test, y_test)) train_acc.append(temp_train_acc) test_acc.append(temp_test_acc) train_acc, test_acc = np.asarray(train_acc), np.asarray(test_acc) print("Best accuracy on CV is {:.2f}% with {} max_depth".format(max(test_acc.mean(axis=1))*100, max_depth_grid[np.argmax(test_acc.mean(axis=1))]))<\/code><\/pre>\n<\/div>\n<\/div>\n <\/p>\n
\u041a\u043e\u0434 \u0434\u043b\u044f \u043f\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u044f \u0433\u0440\u0430\u0444\u0438\u043a\u0430 \u043a\u0440\u0438\u0432\u044b\u0445 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f<\/b><\/p>\n\n
fig, ax = plt.subplots(figsize=(8, 4)) ax.plot(max_depth_grid, train_acc.mean(axis=1), alpha=0.5, color='blue', label='train') ax.plot(max_depth_grid, test_acc.mean(axis=1), alpha=0.5, color='red', label='cv') ax.fill_between(max_depth_grid, test_acc.mean(axis=1) - test_acc.std(axis=1), test_acc.mean(axis=1) + test_acc.std(axis=1), color='#888888', alpha=0.4) ax.fill_between(max_depth_grid, test_acc.mean(axis=1) - 2*test_acc.std(axis=1), test_acc.mean(axis=1) + 2*test_acc.std(axis=1), color='#888888', alpha=0.2) ax.legend(loc='best') ax.set_ylim([0.88,1.02]) ax.set_ylabel("Accuracy") ax.set_xlabel("Max_depth")<\/code><\/pre>\n<\/div>\n<\/div>\n <\/p>\n
![\"image\"\/](\"https:\/\/github.com\/Yorko\/mlcourse_open\/blob\/master\/img\/rf_max_depth.png?raw=true\")
<\/p>\n
<\/p>\n
\u041f\u0430\u0440\u0430\u043c\u0435\u0442\u0440 max_depth<\/code> \u0445\u043e\u0440\u043e\u0448\u043e \u0441\u043f\u0440\u0430\u0432\u043b\u044f\u0435\u0442\u0441\u044f \u0441 \u0440\u0435\u0433\u0443\u043b\u044f\u0440\u0438\u0437\u0430\u0446\u0438\u0435\u0439 \u043c\u043e\u0434\u0435\u043b\u0438, \u0438 \u043c\u044b \u0443\u0436\u0435 \u043d\u0435 \u0442\u0430\u043a \u0441\u0438\u043b\u044c\u043d\u043e \u043f\u0435\u0440\u0435\u043e\u0431\u0443\u0447\u0430\u0435\u043c\u0441\u044f. \u0422\u043e\u0447\u043d\u043e\u0441\u0442\u044c \u043d\u0430\u0448\u0435\u0439 \u043c\u043e\u0434\u0435\u043b\u0438 \u043d\u0435\u043c\u043d\u043e\u0433\u043e \u0432\u043e\u0437\u0440\u043e\u0441\u043b\u0430.<\/p>\n <\/p>\n
\u0415\u0449\u0435 \u0432\u0430\u0436\u043d\u044b\u0439 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440 min_samples_leaf<\/code>, \u043e\u043d \u0442\u0430\u043a \u0436\u0435 \u0432\u044b\u043f\u043e\u043b\u043d\u044f\u0435\u0442 \u0444\u0443\u043d\u043a\u0446\u0438\u044e \u0440\u0435\u0433\u0443\u043b\u044f\u0440\u0438\u0437\u0430\u0442\u043e\u0440\u0430.<\/p>\n <\/p>\n
\u041a\u043e\u0434 \u0434\u043b\u044f \u043f\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u044f \u043a\u0440\u0438\u0432\u044b\u0445 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u043f\u043e \u043f\u043e\u0434\u0431\u043e\u0440\u0443 \u043c\u0438\u043d\u0438\u043c\u0430\u043b\u044c\u043d\u043e\u0433\u043e \u0447\u0438\u0441\u043b\u0430 \u043e\u0431\u044a\u0435\u043a\u0442\u043e\u0432 \u0432 \u043e\u0434\u043d\u043e\u043c \u043b\u0438\u0441\u0442\u0435 \u0434\u0435\u0440\u0435\u0432\u0430<\/b><\/p>\n\n
# \u0421\u043e\u0437\u0434\u0430\u0435\u043c \u0441\u043f\u0438\u0441\u043a\u0438 \u0434\u043b\u044f \u0441\u043e\u0445\u0440\u0430\u043d\u0435\u043d\u0438\u044f \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u0438 \u043d\u0430 \u0442\u0440\u0435\u043d\u0438\u0440\u043e\u0432\u043e\u0447\u043d\u043e\u043c \u0438 \u0442\u0435\u0441\u0442\u043e\u0432\u043e\u043c \u0434\u0430\u0442\u0430\u0441\u0435\u0442\u0435 train_acc = [] test_acc = [] temp_train_acc = [] temp_test_acc = [] min_samples_leaf_grid = [1, 3, 5, 7, 9, 11, 13, 15, 17, 20, 22, 24] # \u041e\u0431\u0443\u0447\u0430\u0435\u043c \u043d\u0430 \u0442\u0440\u0435\u043d\u0438\u0440\u043e\u0432\u043e\u0447\u043d\u043e\u043c \u0434\u0430\u0442\u0430\u0441\u0435\u0442\u0435 for min_samples_leaf in min_samples_leaf_grid: rfc = RandomForestClassifier(n_estimators=100, random_state=42, n_jobs=-1, oob_score=True, min_samples_leaf=min_samples_leaf) temp_train_acc = [] temp_test_acc = [] for train_index, test_index in skf.split(X, y): X_train, X_test = X.iloc[train_index], X.iloc[test_index] y_train, y_test = y[train_index], y[test_index] rfc.fit(X_train, y_train) temp_train_acc.append(rfc.score(X_train, y_train)) temp_test_acc.append(rfc.score(X_test, y_test)) train_acc.append(temp_train_acc) test_acc.append(temp_test_acc) train_acc, test_acc = np.asarray(train_acc), np.asarray(test_acc) print("Best accuracy on CV is {:.2f}% with {} min_samples_leaf".format(max(test_acc.mean(axis=1))*100, min_samples_leaf_grid[np.argmax(test_acc.mean(axis=1))]))<\/code><\/pre>\n<\/div>\n<\/div>\n <\/p>\n
\u041a\u043e\u0434 \u0434\u043b\u044f \u043f\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u044f \u0433\u0440\u0430\u0444\u0438\u043a\u0430 \u043a\u0440\u0438\u0432\u044b\u0445 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f<\/b><\/p>\n\n
fig, ax = plt.subplots(figsize=(8, 4)) ax.plot(min_samples_leaf_grid, train_acc.mean(axis=1), alpha=0.5, color='blue', label='train') ax.plot(min_samples_leaf_grid, test_acc.mean(axis=1), alpha=0.5, color='red', label='cv') ax.fill_between(min_samples_leaf_grid, test_acc.mean(axis=1) - test_acc.std(axis=1), test_acc.mean(axis=1) + test_acc.std(axis=1), color='#888888', alpha=0.4) ax.fill_between(min_samples_leaf_grid, test_acc.mean(axis=1) - 2*test_acc.std(axis=1), test_acc.mean(axis=1) + 2*test_acc.std(axis=1), color='#888888', alpha=0.2) ax.legend(loc='best') ax.set_ylim([0.88,1.02]) ax.set_ylabel("Accuracy") ax.set_xlabel("Min_samples_leaf")<\/code><\/pre>\n<\/div>\n<\/div>\n <\/p>\n
![\"image\"\/](\"https:\/\/github.com\/Yorko\/mlcourse_open\/blob\/master\/img\/rf_leaf.png?raw=true\")
<\/p>\n
<\/p>\n
\u0412 \u0434\u0430\u043d\u043d\u043e\u043c \u0441\u043b\u0443\u0447\u0430\u0435 \u043c\u044b \u043d\u0435 \u0432\u044b\u0438\u0433\u0440\u044b\u0432\u0430\u0435\u043c \u0432 \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u0438 \u043d\u0430 \u0432\u0430\u043b\u0438\u0434\u0430\u0446\u0438\u0438, \u043d\u043e \u0437\u0430\u0442\u043e \u043c\u043e\u0436\u0435\u043c \u0441\u0438\u043b\u044c\u043d\u043e \u0443\u043c\u0435\u043d\u044c\u0448\u0438\u0442\u044c \u043f\u0435\u0440\u0435\u043e\u0431\u0443\u0447\u0435\u043d\u0438\u0435 \u0434\u043e 2% \u043f\u0440\u0438 \u0441\u043e\u0445\u0440\u0430\u043d\u0435\u043d\u0438\u0438 \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u0438 \u043e\u043a\u043e\u043b\u043e 92%.<\/p>\n
<\/p>\n
\u0420\u0430\u0441\u0441\u043c\u043e\u0442\u0440\u0438\u043c \u0442\u0430\u043a\u043e\u0439 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440 \u043a\u0430\u043a max_features<\/code>. \u0414\u043b\u044f \u0437\u0430\u0434\u0430\u0447 \u043a\u043b\u0430\u0441\u0441\u0438\u0444\u0438\u043a\u0430\u0446\u0438\u0438 \u043f\u043e \u0443\u043c\u043e\u043b\u0447\u0430\u043d\u0438\u044e \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u0442\u0441\u044f
![](\"https:\/\/habrastorage.org\/files\/1f8\/981\/50a\/1f898150a862463bae79b42e3da32beb.jpg\")
\u041e\u043a\u043e\u043b\u043e 200 \u0443\u0447\u0430\u0441\u0442\u043d\u0438\u043a\u043e\u0432 \u043f\u043e\u043a\u0430 \u0438\u0434\u0443\u0442 \u0441 \u043c\u0430\u043a\u0441\u0438\u043c\u0430\u043b\u044c\u043d\u044b\u043c \u0431\u0430\u043b\u043b\u043e\u043c. \u041e\u0442\u0442\u043e\u043a \u043d\u0430\u043c\u043d\u043e\u0433\u043e \u043d\u0438\u0436\u0435, \u0447\u0435\u043c \u0432 MOOC-\u0430\u0445, \u0434\u0430\u0436\u0435 \u043d\u0435\u0441\u043c\u043e\u0442\u0440\u044f \u043d\u0430 \u0431\u043e\u043b\u044c\u0448\u043e\u0439 \u043e\u0431\u044a\u0435\u043c \u043d\u0430\u0448\u0438\u0445 \u0441\u0442\u0430\u0442\u0435\u0439. <\/p>\n