Python linear_predictor 예제들

예제 #1

    def test_residuals(self):

        # Input parameters tests
        args = getargspec(residuals)
        self.assertEqual(
            len(args[0]), 2,
            "Expected argument(s) %d, Given %d" % (2, len(args[0])))
        self.assertEqual(
            args[3], None,
            "Expected default values do not match given default values")

        # Return type tests
        dataframe = load_data('data/house_prices_multivariate.csv')
        X_house_prices, y_house_prices = data_splitter(dataframe)
        lm = linear_regression(X_house_prices, y_house_prices)
        y_pred_house_prices, _, ___, __ = linear_predictor(
            lm, X_house_prices, y_house_prices)
        residuals_house_prices = residuals(y_house_prices, y_pred_house_prices)

        self.assertIsInstance(
            residuals_house_prices, pandas.Series,
            "Expected data type for return value is `numpy.ndarray`, you are returning %s"
            % (type(residuals_house_prices)))

        # Return value tests
        self.assertEqual(
            residuals_house_prices.shape, (1379, ),
            "Return `residuals` shape does not match expected value")
        self.assertAlmostEqual(residuals_house_prices.iloc[0], -14665.2446233,
                               2, "Return value does not match expected value")
        self.assertAlmostEqual(residuals_house_prices.iloc[20], 28662.5413679,
                               2, "Return value does not match expected value")
        self.assertAlmostEqual(residuals_house_prices.iloc[30], -28207.3493296,
                               2, "Return value does not match expected value")
        self.assertAlmostEqual(residuals_house_prices.iloc[40], 26990.3010116,
                               2, "Return value does not match expected value")

예제 #2

# %load q05_residuals/build.py
# Default Imports
from greyatomlib.linear_regression.q01_load_data.build import load_data
from greyatomlib.linear_regression.q02_data_splitter.build import data_splitter
from greyatomlib.linear_regression.q03_linear_regression.build import linear_regression
from greyatomlib.linear_regression.q04_linear_predictor.build import linear_predictor
from sklearn.linear_model import LinearRegression

dataframe = load_data('data/house_prices_multivariate.csv')
X, y = data_splitter(dataframe)
linear_model = linear_regression(X, y)
y_pred, _, __, ___ = linear_predictor(linear_model, X, y)


def residuals(y, y_pred):
    error_residuals = (y - y_pred)
    return error_residuals

예제 #3

파일: build.py 프로젝트: rianboy18/linear_regression_project

# %load q05_residuals/build.py
# Default Imports
from greyatomlib.linear_regression.q01_load_data.build import load_data
from greyatomlib.linear_regression.q02_data_splitter.build import data_splitter
from greyatomlib.linear_regression.q03_linear_regression.build import linear_regression
from greyatomlib.linear_regression.q04_linear_predictor.build import linear_predictor
from sklearn.linear_model import LinearRegression

dataframe = load_data('data/house_prices_multivariate.csv')
X, y = data_splitter(dataframe)
linear_model = linear_regression(X, y)
y_pred, mse, mae, r2 = linear_predictor(linear_model, X, y)


def residuals(y, y_pred):
    residuals_house_prices = y - y_pred
    return residuals_house_prices


c = residuals(y, y_pred)
c

예제 #4

파일: test_q05_residuals.py 프로젝트: vp999/linear_regression_project

from unittest import TestCase
from inspect import getargspec
import pandas
from greyatomlib.linear_regression.q01_load_data.build import load_data
from greyatomlib.linear_regression.q02_data_splitter.build import data_splitter
from greyatomlib.linear_regression.q04_linear_predictor.build import linear_predictor
from greyatomlib.linear_regression.q03_linear_regression.build import linear_regression
from ..build import residuals

dataframe = load_data('data/house_prices_multivariate.csv')
X_house_prices, y_house_prices = data_splitter(dataframe)
lm = linear_regression(X_house_prices, y_house_prices)
y_pred_house_prices, _, ___, __ = linear_predictor(lm, X_house_prices,
                                                   y_house_prices)
residuals_house_prices = residuals(y_house_prices, y_pred_house_prices)


class TestResiduals(TestCase):
    def test_residuals_arguments(self):

        # Input parameters tests
        args = getargspec(residuals)
        self.assertEqual(
            len(args[0]), 2,
            "Expected argument(s) %d, Given %d" % (2, len(args[0])))

    def test_residuals_defaults(self):
        args = getargspec(residuals)
        self.assertEqual(
            args[3], None,
            "Expected default values do not match given default values")

예제 #5

파일: build.py 프로젝트: santoshmayekar/linear_regression_project

# Default Imports
from greyatomlib.linear_regression.q01_load_data.build import load_data
from greyatomlib.linear_regression.q02_data_splitter.build import data_splitter
from greyatomlib.linear_regression.q03_linear_regression.build import linear_regression
from greyatomlib.linear_regression.q04_linear_predictor.build import linear_predictor
from greyatomlib.linear_regression.q05_residuals.build import residuals
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt

import pylab
import scipy.stats as stats


dataframe = load_data('data/house_prices_multivariate.csv')
X, y = data_splitter(dataframe)
linear_model = linear_regression(X, y)
y_pred,MSE_sklearn,MAE_sklearn, r2_sklearn = linear_predictor(linear_model, X, y)
error_residuals = residuals(y, y_pred)

def qq_residuals(error_residuals):
    stats.probplot(error_residuals, dist="norm", plot=pylab)
    pylab.show()

예제 #6

# %load q06_plot_residuals/build.py
# Default Imports
from greyatomlib.linear_regression.q01_load_data.build import load_data
from greyatomlib.linear_regression.q02_data_splitter.build import data_splitter
from greyatomlib.linear_regression.q03_linear_regression.build import linear_regression
from greyatomlib.linear_regression.q04_linear_predictor.build import linear_predictor
from greyatomlib.linear_regression.q05_residuals.build import residuals
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt
plt.switch_backend('agg')

dataframe = load_data('data/house_prices_multivariate.csv')
X, y = data_splitter(dataframe)
linear_model = linear_regression(X, y)
y_pred, rms, rma, r2 = linear_predictor(linear_model, X, y)
error_residuals = residuals(y, y_pred)


# Your code here
def plot_residuals(y, error_residuals):

    plt.figure(figsize=(10, 4))
    plt.scatter(y, error_residuals)
    plt.xlabel('Sale price')
    plt.ylabel('Errors')
    plt.title('Residual plot')
    plt.show()


plot_residuals(y, error_residuals)

예제 #7

파일: build.py 프로젝트: naitik1995/linear_regression_project

# %load q08_qq_residuals/build.py
# Default Imports
from greyatomlib.linear_regression.q01_load_data.build import load_data
from greyatomlib.linear_regression.q02_data_splitter.build import data_splitter
from greyatomlib.linear_regression.q03_linear_regression.build import linear_regression
from greyatomlib.linear_regression.q04_linear_predictor.build import linear_predictor
from greyatomlib.linear_regression.q05_residuals.build import residuals
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt

import pylab
import scipy.stats as stats

dataframe = load_data('data/house_prices_multivariate.csv')
X, y = data_splitter(dataframe)
linear_model = linear_regression(X, y)
y_pred, y_mse, y_mae, y_r2 = linear_predictor(linear_model, X, y)
error_residuals = residuals(y, y_pred)


# Your code here
def qq_residuals(error_residuals):
    stats.probplot(error_residuals, dist='norm', plot=pylab)
    pylab.title('Probabality Plot')
    pylab.ylabel('Ordered Values')
    pylab.xlabel('Theoretical quantiles')
    pylab.show()