def pyfora_linear_regression_test(self):
random.seed(42)
nRows = 100
x_col_1 = []
x_col_2 = []
y_col = []
for _ in range(nRows):
x1 = random.uniform(-10, 10)
x2 = random.uniform(-10, 10)
noise = random.uniform(-1, 1)
y = x1 * 5 + x2 * 2 - 8 + noise
x_col_1.append(x1)
x_col_2.append(x2)
y_col.append(y)
def computeCoefficients():
predictors = PurePandas.PurePythonDataFrame([x_col_1, x_col_2], ["x1", "x2"])
responses = PurePandas.PurePythonDataFrame([y_col], ["y"])
return LinearRegression.linearRegression(predictors, responses)
res_python = computeCoefficients()
res_pyfora = self.evaluateWithExecutor(computeCoefficients)
self.assertArraysAreAlmostEqual(res_python, res_pyfora)
df_x = pandas.DataFrame({
'x1': x_col_1,
'x2': x_col_2
})
df_y = pandas.DataFrame({
'y': y_col
})
res_pandas = LinearRegression.linearRegression(df_x, df_y)
self.assertArraysAreAlmostEqual(res_python, res_pandas)
# verified using sklearn.linear_model.LinearRegression, on nRows = 100
res_scikit = numpy.array([[4.96925412, 2.00279298, -7.98208391]])
self.assertArraysAreAlmostEqual(res_python, res_scikit)
def computeCoefficients():
predictors = PurePandas.PurePythonDataFrame([x_col_1, x_col_2], ["x1", "x2"])
responses = PurePandas.PurePythonDataFrame([y_col], ["y"])
return LinearRegression.linearRegression(predictors, responses)
