def decision_tree_depths():
max_depths = [2, 4, 6, 8, 10, 12, 16, 18, 20, 25, 30, 40]
columns = [
'Max Depths', 'Training Score', 'Test Score', 'Train Time', 'Test Time'
]
df = pd.DataFrame(columns=columns)
for depth in max_depths:
start_train = time.time()
dt = DecisionTreeClassifier(max_depth=depth)
print(dt)
dt.fit(X_train, y_train)
end_train = time.time() - start_train
train_score = dt.score(X_train, y_train)
start_test = time.time()
test_score = dt.score(X_test, y_test)
end_test = time.time() - start_test
values = [depth, train_score, test_score, end_train, end_test]
df.loc[len(df)] = values
print(' '.join(str(col) for col in columns))
print(' '.join(str(val) for val in values))
df.to_excel('adult_dt.xls')
def decision_tree_training_sets():
training_set_sizes = [.1,.25,.5,.75,.9]
columns = ['Training Set Size', 'Training Score', 'Test Score', 'Train Time', 'Test Time']
df = pd.DataFrame(columns=columns)
for training_set_size in training_set_sizes:
X_train, X_test, y_train, y_test = train_test_split(
encoded_data[list(set(encoded_data.columns) - set(['Target']))],
encoded_data['Target'], train_size=training_set_size)
scaler = preprocessing.StandardScaler()
X_train = pd.DataFrame(scaler.fit_transform(X_train.astype('float32')), columns=X_train.columns)
X_test = scaler.transform(X_test.astype('float32'))
start_train = time.time()
dt = DecisionTreeClassifier(max_depth=8)
print(dt)
dt.fit(X_train, y_train)
end_train = time.time() - start_train
train_score = dt.score(X_train, y_train)
start_test = time.time()
test_score = dt.score(X_test, y_test)
end_test = time.time() - start_test
values = [training_set_size, train_score, test_score, end_train, end_test]
df.loc[len(df)] = values
print(' '.join(str(col) for col in columns))
print(' '.join(str(val) for val in values))
df.to_excel('diabetes_dt_training_sets.xls')
def sklearn_titanic():
from sklearn.tree.tree import DecisionTreeClassifier
from sklearn.preprocessing.label import LabelEncoder
total_df = pd.read_csv("titanic_clean.csv")
total_df.drop(['cabin', 'boat', 'body', 'index'], axis=1, inplace=True)
total_df.dropna(inplace=True)
for col in total_df.columns.tolist():
if str(total_df[col].dtype) == 'object':
total_df[col] = LabelEncoder().fit_transform(total_df[col])
total_num = total_df.shape[0]
train_df = total_df.iloc[:int(total_num * 0.8)]
test_df = total_df.iloc[int(total_num * 0.8):]
clf = DecisionTreeClassifier()
clf.fit(train_df.drop(['survived'], axis=1), train_df['survived'])
print(clf.score(test_df.drop(['survived'], axis=1), test_df['survived']))
from numpy import loadtxt
from sklearn.model_selection import train_test_split
from sklearn.tree.tree import DecisionTreeClassifier
func = lambda x: 0.0 if x == b'False' else 1.0
all_data = loadtxt('flare.csv',
delimiter=',',
skiprows=1,
converters={32: func})
target = all_data[:, -1]
data = all_data[:, 0:-1]
train_x, test_x, train_y, test_y = train_test_split(data,
target,
test_size=0.25,
random_state=100)
# SEIF A - Train the tree without trimming
clf = DecisionTreeClassifier(criterion="entropy")
clf.fit(train_x, train_y)
success_rate = clf.score(test_x, test_y)
# SEIF B - Trim to leaves smaller or equal to 20
clf = DecisionTreeClassifier(criterion="entropy", min_samples_leaf=20)
clf.fit(train_x, train_y)
success_rate = clf.score(test_x, test_y)
