def test_My_Random_Forest_Classifier_predict():
# Object Declarations
# Tests with N = 3, M = 2, F = 2 and seed = 1
rand_forest_test = MyRandomForestClassifier(3, 2, 2, 1)
table = MyPyTable()
# Variable Assignment and Declaration
table.data = interview_table
table.column_names = interview_header
y_train, X_train = [], []
for inst in interview_table:
y_train.append(inst[-1])
X_train.append(inst[:-1])
# Sets X_test
X_test = [["Junior", "Java", "yes", "no"],
["Junior", "Java", "yes", "yes"]]
# Tests on the Interview Dataset
rand_forest_test.header = interview_header[:-1]
rand_forest_test.fit(X_train, y_train)
y_predicted = rand_forest_test.predict(X_test)
print("y_predicted:", y_predicted)
# Trace Test
assert y_predicted == ['True', 'False']
def confusionCategorical(yTrue, yTest, header, categories):
table = MyPyTable()
table.column_names = header
table.data = []
for val in categories:
newRow = [val]
for i in range(len(header) - 1):
newRow.append(0)
table.data.append(newRow)
for i in range(len(yTrue)):
rowIndex = categories.index(yTrue[i])
colIndex = header.index(yTest[i])
table.data[rowIndex][colIndex] += 1
for row in table.data:
total = 0
for i in range(1, len(categories) + 1):
total += row[i]
row[len(categories) + 1] = total
for i in range(len(table.data)):
if table.data[i][len(categories) + 1] != 0:
recognition = table.data[i][i +
1] / table.data[i][len(categories) + 1]
table.data[i][len(header) - 1] = round(100 * recognition, 2)
return table
def test_My_Random_Forest_Classifier_fit():
# Object Declarations
# Tests with N = 3, M = 2, F = 2 and seed = 0
rand_forest_test = MyRandomForestClassifier(3, 2, 2, 0)
table = MyPyTable()
# Variable Assignment and Declaration
table.data = interview_table
table.column_names = interview_header
X_test = interview_table
y_train = table.get_column("interviewed_well")
# Tests on the Interview Dataset
rand_forest_test.header = interview_header
rand_forest_test.fit(X_test, y_train)
trees = rand_forest_test.trees
from mysklearn.mypytable import MyPyTable
# Object Declaration
table = MyPyTable()
# Trims the Dataset (Gets Data Based on City)
city = "Sydney"
table.load_from_file("weatherAUS.csv")
table.column_names[0] = 'Location'
names, tables = table.group_by("Location")
city_index = names.index(city)
print("\n")
for i in range(10):
print(tables[city_index][i])
table.data = tables[city_index]
table.save_to_file(city+"_weather.csv")