def test_split_data_2():
'''
Test to determine proportion of split is correct
'''
total_length = len(data)
df = clean_split_data.clean_data(data)
X_train, X_test, y_train, y_test = clean_split_data.split_data(df)
train_length = len(X_train)
train_split = train_length / total_length
assert math.isclose(
train_split, 0.80,
abs_tol=0.1), ("Training set is not at specified 80% of dataset")
return
def test_split_data_1():
'''
Test to determine total length of datafile did not change when splitting
'''
total_length = len(data)
df = clean_split_data.clean_data(data)
X_train, X_test, y_train, y_test = clean_split_data.split_data(df)
train_length = len(X_train)
test_length = len(X_test)
total_split = train_length + test_length
assert math.isclose(
total_length,
total_split), ("Length of data is not the same as before splitting")
return
import pandas as pd
# Import Scikit-Learn library for decision tree models
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
# Import plotting libraries
import matplotlib
# Set larger fontsize for all plots
matplotlib.rcParams.update({'font.size': 18})
# ### Data
data = pd.read_csv('data/data.csv')
data = clean_data(data)
X_train, X_test, y_train, y_test = split_data(data)
# ### Classifier
clf = DecisionTreeClassifier(max_depth=5)
clf.fit(X_train, y_train)
# ### Optimized Decision Tree Predictor
def feature_names():
'''
Returns array of input features of best
performing backwards stepwise selection test.
'''
return [
'radius_mean', 'texture_mean', 'perimeter_mean', 'area_mean',