def test_random_forest_fit():
interview_header = ["level", "lang", "tweets", "phd", "interviewed_well"]
interview_table = [["Senior", "Java", "no", "no", "False"],
["Senior", "Java", "no", "yes", "False"],
["Mid", "Python", "no", "no", "True"],
["Junior", "Python", "no", "no", "True"],
["Junior", "R", "yes", "no", "True"],
["Junior", "R", "yes", "yes", "False"],
["Mid", "R", "yes", "yes", "True"],
["Senior", "Python", "no", "no", "False"],
["Senior", "R", "yes", "no", "True"],
["Junior", "Python", "yes", "no", "True"],
["Senior", "Python", "yes", "yes", "True"],
["Mid", "Python", "no", "yes", "True"],
["Mid", "Java", "yes", "no", "True"],
["Junior", "Python", "no", "yes", "False"]]
myutils.prepend_attribute_label(interview_table, interview_header)
interview_pytable = MyPyTable(column_names=interview_header,
data=interview_table)
y_col = interview_pytable.get_column("interviewed_well", False)
x_cols = interview_pytable.drop_col("interviewed_well")
many_trees = MyRandomForestClassifier()
X_sample, y_sample = myutils.compute_bootstrapped_sample(x_cols, y_col)
X_train, X_test, y_train, y_test = myutils.train_test_split(
X_sample, y_sample, .33)
many_trees.fit(X_train, y_train, X_test, y_test)
y_predicted = many_trees.predict(X_test)
numCorrectPredictions = 0
numWrongPredictions = 0
for i in range(len(y_test)):
values = [y_predicted[i], y_test[i]] #predicted/actual
if (values[0] == values[1]):
numCorrectPredictions = numCorrectPredictions + 1
else:
numWrongPredictions = numWrongPredictions + 1
accuracy = np.round((numCorrectPredictions) /
(numCorrectPredictions + numWrongPredictions), 3)
error_rate = np.round(
(numWrongPredictions) / (numCorrectPredictions + numWrongPredictions),
3)
print("-----------------------------------------------------------")
print("Accuracy and Error Rate")
print("-----------------------------------------------------------")
print()
print("Random Forest: accuracy = {}, error rate = {}".format(
accuracy, error_rate))
print()
print(
"Because of the random aspect of this classifier, this will not always pass the tests"
)
print()
print("Predicted table: " + str(y_predicted))
print("Testing set: " + str(y_test))
for i in range(len(y_test)):
assert y_predicted[i] == y_test[i]
from mysklearn.myclassifiers import MyDecisionTreeClassifier, MyNaiveBayesClassifier
import mysklearn.myevaluation as myevaluation
import mysklearn.myutils as myutils
import os
# "pickle" an object (AKA object serialization)
# save a Python object to a binary file
# "unpickle" an object (AKA object de-serialization)
# load a Python object from a binary file (back into memory)
# Get data from csv file
table = MyPyTable().load_from_file(
os.path.join("input_files", "winequality-red.csv"))
y_col = table.get_column("quality", False)
x_cols = table.drop_col("quality")
# Use Naive Bayes to classify
testcase = MyNaiveBayesClassifier()
#Returns x INDEXES
X_train, X_test = myevaluation.stratified_kfold_cross_validation(x_cols,
y_col,
n_splits=10)
X_train, X_test, y_train, y_test = myutils.getInstances(
X_train, X_test, x_cols, y_col)
for i, fold in enumerate(X_train):
train, test = myutils.normalize_values(X_train[i], X_test[i])
testcase.fit(train, y_train[i])
break