def test_clean_data_6():
'''
Test to determine if diagnosis values are replaced with integers
'''
df = clean_split_data.clean_data(data)
diagnosis = df.diagnosis
for cancer in diagnosis:
assert isinstance(cancer, int), ("Diagnosis values are not integers")
return
def test_clean_data_4():
'''
Test to determine if "id" column was successfully dropped from dataframe
'''
df = clean_split_data.clean_data(data)
names = df.columns
substring = "id"
for name in names:
assert substring not in name, ("ID column still exists in dataframe")
return
def test_clean_data_1():
'''
Test to determine if data column contains all strings
'''
df = clean_split_data.clean_data(data)
names = df.columns
for name in names:
assert isinstance(name, str), (
"Data columns are not all strings, there may be a filtering error")
return
def test_clean_data_3():
'''
Test to determine if any of the data contains strings "_worst"
'''
df = clean_split_data.clean_data(data)
names = df.columns
substring = "_worst"
for name in names:
assert substring not in name, (
"Worst measurement columns still exist in dataframe")
return
def test_clean_data_2():
'''
Test to determine if any of the data contains strings "_se"
'''
df = clean_split_data.clean_data(data)
names = df.columns
substring = "_se"
for name in names:
assert substring not in name, (
"Standard error columns still exist in dataframe")
return
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
def stacking_predictor(row):
"""
Training stacking model with our data
Define what our base layer will be composed of and then build
a stacking classifier base
on these models.
set our final estimator as "logistic regression"
"""
our_trained_data = pd.read_csv("data/data.csv")
our_trained_data = clean_data(our_trained_data)
x = our_trained_data[[
'radius_mean', 'texture_mean', 'area_mean', 'concavity_mean',
'concave points_mean', 'symmetry_mean', 'smoothness_mean'
]]
y = our_trained_data[['diagnosis']]
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.2,
random_state=42)
x_train = x_train.values.tolist()
y_train = y_train.values.tolist()
flattened_y_train = []
for sub_list in y_train:
for val in sub_list:
flattened_y_train.append(val)
X, y = x_train, flattened_y_train
estimators = [('random_forest',
RandomForestClassifier(n_estimators=5, random_state=42)),
('logistic_regr',
LogisticRegression(solver="lbfgs", max_iter=1460)),
('knn', KNeighborsClassifier(n_neighbors=5)),
('svm_rbf', SVC(kernel='rbf', gamma=4, C=10000))]
Stacking_classifier = StackingClassifier(
estimators=estimators, final_estimator=LogisticRegression(), cv=5)
# Fit the stacking model with our own data and with selected 7 features.
Stacking_classifier.fit(X, y)
# Now predicting one patient
single_predicted_result = Stacking_classifier.predict([row])
return ('%s %d' % ("patient", single_predicted_result))
# Pandas library for the pandas dataframes
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 [
