def get_tree_results(tree, Xtest):
"""
Runs data through a quantized DecisionTreeClassifier
:param tree: DTC function handle
:param Xtest: data to test
:returns: predicted results
"""
results = [tree(X) for X in Xtest]
return np.array([results], ndmin=1).T
def select_classify():
return [
naive(),
tree(criterion="entropy"),
knn(n_neighbors=8, weights='uniform', metric="manhattan"),
mlp(hidden_layer_sizes=(128, ),
alpha=0.01,
activation='tanh',
solver='sgd',
max_iter=300,
learning_rate='constant',
learning_rate_init=0.001)
]
print('CM:', confusion_matrix(y_test, y_pred))
print('AC:', ac(y_test, y_pred))
print('F1 scores:', f1(y_test, y_pred))
print('PR:', prfs(y_test, y_pred))
from sklearn.naive_bayes import GaussianNB
model5 = GaussianNB().fit(X_train, y_train)
y_pred = model5.predict(X_test)
print('CM:', confusion_matrix(y_test, y_pred))
print('AC:', ac(y_test, y_pred))
print('F1 scores:', f1(y_test, y_pred))
print('PR:', prfs(y_test, y_pred))
from sklearn.tree import DecisionTreeClassifier as tree
model6 = tree(criterion='entropy').fit(X_train, y_train)
y_pred = model6.predict(X_test)
print('CM:', confusion_matrix(y_test, y_pred))
print('AC:', ac(y_test, y_pred))
print('F1 scores:', f1(y_test, y_pred))
print('PR:', prfs(y_test, y_pred))
from sklearn.ensemble import RandomForestClassifier as forest
model7 = forest(max_depth=5).fit(X_train, y_train)
y_pred = model7.predict(X_test)
print('CM:', confusion_matrix(y_test, y_pred))
print('AC:', ac(y_test, y_pred))
print('F1 scores:', f1(y_test, y_pred))
print('PR:', prfs(y_test, y_pred))
features_train = vectorizer.fit_transform(features_train) features_test = vectorizer.transform(features_test).toarray() ### a classic way to overfit is to use a small number ### of data points and a large number of features; ### train on only 150 events to put ourselves in this regime features_train = features_train[:150].toarray() labels_train = labels_train[:150] ### your code goes here print len(labels_train) print len(features_train) clf = tree(min_samples_split=40) clf.fit(features_train, labels_train) pred = clf.predict(features_test) accuracy = accuracy_score(pred,labels_test) print accuracy #after removing 2 sig words 0.816837315131 print 'Importance of the most important feature:' #0.764705882353 print max(clf.feature_importances_) print 'Number of most important feature:' #33614 print list(clf.feature_importances_).index(max(clf.feature_importances_)) print list(clf.feature_importances_)[-1] #sshacklensf cgermannsf
from sklearn.tree import DecisionTreeClassifier as tree from sklearn.svm import SVC as svm from sklearn.model_selection import train_test_split from sklearn.ensemble import RandomForestClassifier from sklearn import metrics data_set = ds.load_digits() x = data_set.data y = data_set.target X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.3, random_state=0) neighbors_model = KNeighborsClassifier(n_neighbors=3) bayes_model = naive_bayes() tree_model = tree() svm_model = svm() forest_model = RandomForestClassifier() neighbors_model.fit(X_train, y_train) bayes_model.fit(X_train, y_train) tree_model.fit(X_train, y_train) svm_model.fit(X_train, y_train) forest_model.fit(X_train, y_train) y_actual_neighbors = neighbors_model.predict(X_test) y_actual_bayes = bayes_model.predict(X_test) y_actual_tree = tree_model.predict(X_test) y_actual_svm = svm_model.predict(X_test) y_actual_forest = forest_model.predict(X_test)
def classifierTrainTest(score, diagn, real_art, cvPartition, classifier,
subjIndex, preAccMatrix, preInstOrder):
x = 0
iteration = 0
idx = 0
PCNo = len(score[0])
subAccMatrix = 0
# FIX: what is test->matlab function within cvpartition class
#idx = numpy.random.rand(cvPartition, iteration)
#idx_test = numpy.where(idx == 1)
#idx_train = numpy.where(idx != 1)
print("cvPartition:")
print(cvPartition)
#QUESTION: cv partition not scalar ,how works
#iteration must be atleast 2
for idx_train, idx_test in cvPartition:
#change idx to boolean array
idx = numpy.zeros((len(score), 1), dtype=bool)
for index in idx_test:
idx[index] = True
#for testing purposes
#idx = numpy.zeros((len(score), 1), dtype=bool)
#idx[47] = True
#idx is all training in MATLAB implementation?
cvTEST = numpy.zeros((sum(idx), PCNo))
diagnTEST = numpy.zeros((sum(idx), 1))
real_artTEST = numpy.zeros((sum(idx), 1))
instIndexTEST = numpy.zeros((sum(idx), 1))
cvTRAIN = numpy.zeros((len(idx) - sum(idx), PCNo))
diagnTRAIN = numpy.zeros((len(idx) - sum(idx), 1))
real_artTRAIN = numpy.zeros((len(idx) - sum(idx), 1))
k = 0
m = 0
for j in range(len(idx)):
if idx[j] == 1:
cvTEST[k, :] = score[j, :]
diagnTEST[k] = diagn[j]
real_artTEST[k] = real_art[j]
instIndexTEST[k] = subjIndex[j]
k = k + 1
else:
cvTRAIN[m, :] = score[j, :]
diagnTRAIN[m] = diagn[j]
real_artTRAIN[m] = real_art[j]
m = m + 1
# FIX: use scikit-learn for classifiers and predictions
if classifier == "lda":
#ldaModel = LDA()
priorsArrays = numpy.array((.5, .5))
ldaModel = LDA(solver='eigen',
priors=priorsArrays,
shrinkage=1.00)
#ldaModel = LDA()
ldaModel.fit(cvTRAIN, diagnTRAIN)
label = ldaModel.predict(cvTEST)
elif classifier == 'qda':
# training a quadratic discriminant classifier to the data
#qdaModel = QDA()
priorsArrays = numpy.array((.5, .5))
qdaModel = QDA(solver='eigen',
priors=priorsArrays,
shrinkage=1.00)
qdaModel.fit(cvTRAIN, diagnTRAIN)
label = qdaModel.predict(cvTEST)
elif classifier == 'tree':
# training a decision tree to the data
treeModel = tree()
treeModel.fit(cvTRAIN, diagnTRAIN)
label = treeModel.predict(cvTEST)
elif classifier == 'svm':
# training a support vector machine to the data
svmModel = SVC()
svmModel.fit(cvTRAIN, diagnTRAIN)
label = svmModel.predict(cvTEST)
trueClassLabel = diagnTEST
predictedClassLabel = label
#from former loop
subAccMatrix = numpy.column_stack(
(trueClassLabel, predictedClassLabel, real_artTEST))
preAccMatrix[x:x + len(subAccMatrix[:, 0]), :] = subAccMatrix
preInstOrder[x:x + len(instIndexTEST[:, 0])] = instIndexTEST
x = x + len(subAccMatrix[:, 0])
#for testing purposes
#break
# create dictionary for return values
return {
'cvTEST': cvTEST,
'diagnTEST': diagnTEST,
'real_artTEST': real_artTEST,
'instIndexTEST': instIndexTEST,
'cvTRAIN': cvTRAIN,
'diagnTRAIN': diagnTRAIN,
'real_artTRAIN': real_artTRAIN,
'trueClassLabel': trueClassLabel,
'predictedClassLabel': predictedClassLabel,
'idx': idx,
'subAccMatrix': subAccMatrix,
'preAccMatrix': preAccMatrix,
'preInstOrder': preInstOrder
}
x = data_set.data
y = data_set.target
cv_kfold = KFold(n_splits=30)
neighbors_classifiers = []
bayes_classifiers = []
tree_classifiers = []
svm_classifiers = []
forest_classifiers = []
for train_index, test_index in cv_kfold.split(y):
neighbors_model = KNeighborsClassifier(n_neighbors=3)
bayes_model = naive_bayes()
tree_model = tree()
svm_model = svm()
forest_model = RandomForestClassifier()
X_train, X_test = x[train_index], x[test_index]
y_train, y_test = y[train_index], y[test_index]
neighbors_model.fit(X_train, y_train)
bayes_model.fit(X_train, y_train)
tree_model.fit(X_train, y_train)
svm_model.fit(X_train, y_train)
forest_model.fit(X_train, y_train)
neighbors_classifiers.append(neighbors_model)
bayes_classifiers.append(bayes_model)
tree_classifiers.append(tree_model)
svm_classifiers.append(svm_model)
def mean_error(max_leaf_nodes, train_X, val_X, train_y, val_y):
model = tree(max_leaf_nodes=max_leaf_nodes, random_state=0)
model.fit(train_X, train_y)
prediction = model.predict(val_X)
return mean_absolute_error(val_y, prediction)
clf.fit(X_train, y_train)
y_predicted = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_predicted)
f1 = f1_score(y_test, y_predicted, average="weighted")
return accuracy, f1
#%%
from sklearn.tree import DecisionTreeClassifier as tree
from sklearn.ensemble import BaggingClassifier,RandomForestClassifier,AdaBoostClassifier,GradientBoostingClassifier
from xgboost import XGBClassifier
classifiers = {
'DecisionTree':tree(splitter='best', min_samples_split=10, min_samples_leaf= 6, max_features=100,
max_depth= 30, criterion= 'gini'),
'Bagging':BaggingClassifier(n_estimators= 300, max_samples =0.7999999999999999,max_features=40),
'RandomForest':RandomForestClassifier(n_estimators= 230, min_samples_split= 2, min_samples_leaf=2,
max_features=70, max_depth=45),
'AdaBoost':AdaBoostClassifier(n_estimators=260, learning_rate=0.001,
base_estimator=tree(class_weight=None, criterion='gini', max_depth=10,
max_features=30, max_leaf_nodes=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=5, min_samples_split=5,
min_weight_fraction_leaf=0.0, presort=False, random_state=None,
splitter='best')),
'GradientBoostingTree':GradientBoostingClassifier(n_estimators=175,min_samples_split=2,
data_dict = pickle.load(open("../final_project/final_project_dataset.pkl", "r") )
### add more features to features_list!
features_list = ["poi", "salary"]
data = featureFormat(data_dict, features_list)
labels, features = targetFeatureSplit(data)
### your code goes here
features_train, features_test, labels_train, labels_test = cross_validation.train_test_split(features, labels, test_size=0.3, random_state=42)
clf = tree()
clf.fit(features_train, labels_train)
pred = clf.predict(features_test)
accuracy = accuracy_score(pred,labels_test)
print accuracy #0.724137931034
print np.array(labels_test)
print "number of POIs in the test set:"
num_pois_test = len([x for x in labels_test if x == 1.0])
print num_pois_test
print "total people in the test set:"
total_ppl_test= len(labels_test)
print total_ppl_test
print "If your identifier predicted 0. (not POI) for everyone in the test set, what would its accuracy be?"
acc = 1.0 - float(num_pois_test)/total_ppl_test
print acc
'max_depth': np.arange(1, 6),
'min_samples_split': np.arange(3, 8),
'min_samples_leaf': np.arange(1, 5)
}
params_rs = {
'criterion': ('entropy', 'gini'),
'splitter': ('best', 'random'),
'max_depth': randint(1, 6),
'min_samples_split': randint(3, 8),
'min_samples_leaf': randint(1, 5)
}
# In[88]:
model = tree()
gs = GridSearchCV(tree(), cv=10, param_grid=params_gs, scoring='accuracy')
gs.fit(x_tr, y_tr)
# In[89]:
cv_score_gs = []
final_score_gs = []
for i in range(0, 100):
print('Iteracja: ' + str(i))
gs = GridSearchCV(tree(),
cv=10,
param_grid=params_gs,
scoring='accuracy',
n_jobs=-1)