睡眠健康数据分析（下）

df = df.drop('Person ID', axis = 1)

hot = pd.get_dummies(df[['Gender', 'Occupation', 'BMI Category', 'Blood Pressure']])
df = pd.concat([df, hot], axis = 1)
df = df.drop(['Gender', 'Occupation', 'BMI Category', 'Blood Pressure'], axis = 1)

X = df.drop('Sleep Disorder', axis = 1)
X = X.values
y = df['Sleep Disorder']

from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X_standard = scaler.fit_transform(X)

from sklearn.model_selection import train_test_split
X_train,X_test, y_train, y_test = train_test_split(X_standard, y, test_size = 0.3, random_state = 0)

from sklearn.naive_bayes import GaussianNB
naive_bayes = GaussianNB()
naive_bayes.fit(X_train, y_train)
previsoes = naive_bayes.predict(X_test)
cm = ConfusionMatrix(naive_bayes)
cm.fit(X_train, y_train)
cm.score(X_test, y_test)

score_naive_gaussian = 0.530973451327433

parameters = {'max_depth': [3, 4, 5, 6, 7, 9, 11],
              'min_samples_split': [2, 3, 4, 5, 6, 7],
              'criterion': ['entropy', 'gini']
             }
model = DecisionTreeClassifier()
gridDecisionTree = RandomizedSearchCV(model, parameters, cv = 3, n_jobs = -1)
gridDecisionTree.fit(X_train, y_train)
print('Mín Split: ', gridDecisionTree.best_estimator_.min_samples_split)
print('Max Nvl: ', gridDecisionTree.best_estimator_.max_depth)
print('Algorithm: ', gridDecisionTree.best_estimator_.criterion)
print('Score: ', gridDecisionTree.best_score_)

score_tree = 0.8938053097345132

from sklearn.ensemble import RandomForestClassifier
parameters = {'max_depth': [3, 4, 5, 6, 7, 9, 11],
              'min_samples_split': [2, 3, 4, 5, 6, 7],
              'criterion': ['entropy', 'gini']
             }
model = RandomForestClassifier()
gridRandomForest = RandomizedSearchCV(model, parameters, cv = 5, n_jobs = -1)
gridRandomForest.fit(X_train, y_train)
print('Algorithm: ', gridRandomForest.best_estimator_.criterion)
print('Score: ', gridRandomForest.best_score_)
print('Mín Split: ', gridRandomForest.best_estimator_.min_samples_split)
print('Max Nvl: ', gridRandomForest.best_estimator_.max_depth)

random_forest = RandomForestClassifier(n_estimators = 100, min_samples_split = 5, max_depth= 5,  criterion = 'gini', random_state = 0)
random_forest.fit(X_train, y_train)
previsoes = random_forest.predict(X_test)
cm = ConfusionMatrix(random_forest)
cm.fit(X_train, y_train)
cm.score(X_test, y_test)

score_random = 0.9026548672566371

feature_imp_random = pd.Series(random_forest.feature_importances_, index = columns).sort_values(ascending = False)
feature_imp_random

score_extra = 0.8849557522123894
• 1

from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier()
k_list = list(range(1,10))
k_values = dict(n_neighbors = k_list)
grid = GridSearchCV(knn, k_values, cv = 2, scoring = 'accuracy', n_jobs = -1)
grid.fit(X_train, y_train)
grid.best_params_, grid.best_score_

knn = KNeighborsClassifier(n_neighbors = 5, metric = 'minkowski', p = 2)
knn.fit(X_train, y_train)
previsoes = knn.predict(X_test)
cm = ConfusionMatrix(knn)
cm.fit(X_train, y_train)
cm.score(X_test, y_test)

score_knn = 0.8849557522123894

from sklearn.linear_model import LogisticRegression
logistic = LogisticRegression(random_state = 1, max_iter=10000)
logistic.fit(X_train, y_train)
previsoes = logistic.predict(X_test)
cm = ConfusionMatrix(logistic)
cm.fit(X_train, y_train)
cm.score(X_test, y_test)

logistic_normal = 0.911504424778761
•

from sklearn.ensemble import AdaBoostClassifier
parameters = {'learning_rate': [0.01, 0.02, 0.05, 0.07, 0.09, 0.1, 0.3, 0.001, 0.005],
              'n_estimators': [300, 500]
             }
model = AdaBoostClassifier()
gridAdaBoost = RandomizedSearchCV(model, parameters, cv = 2, n_jobs = -1)
gridAdaBoost.fit(X_train, y_train)
print('Learning Rate: ', gridAdaBoost.best_estimator_.learning_rate)
print('Score: ', gridAdaBoost.best_score_)

ada_boost = AdaBoostClassifier(n_estimators = 500, learning_rate =  0.02, random_state = 0)
ada_boost.fit(X_train, y_train)
previsoes = ada_boost.predict(X_test)
cm = ConfusionMatrix(ada_boost)
cm.fit(X_train, y_train)
cm.score(X_test, y_test)

score_ada_scaler = 0.911504424778761