def main():
boston_dstl = DatasetsTools(datasets.load_boston)
# print(str(boston_dstl))
boston_df = boston_dstl.data_as_df()
print(boston_dstl.info)
def set_CHAS(n):
if (n == 1):
return "bounds river"
else:
None
boston_df.CHAS = boston_df.CHAS.apply(set_CHAS)
plotter = DataPlots(df=boston_df, ggplot=True, cmap=cm.jet)
sizes_lst = [(4, 4), (6, 4), (6, 4), (12, 8), (7, 7), (6, 6), (6, 6),
(12, 12), (12, 12), (12, 12), (12, 12), (12, 12), (12, 12),
(12, 12), (12, 12)]
# plotter.plot_column(data_column=boston_df.CHAS)
# plt.show()
for i, col in enumerate(list(boston_df)):
print(col)
plotter.plot_column(data_column=boston_df[col], figsize=sizes_lst[i])
plt.show()
return
def main():
# load iris data into DataFrame
iris_dtst = DatasetsTools(datasets.load_iris)
iris_df = iris_dtst.data_as_df()
print("columns: {}".format(list(iris_df)))
print(iris_dtst.info)
# iris-colored_acatter_matrix in 3 lines of code
plotter = DataPlots(df=iris_df, ggplot=True, is_verbose=True)
fig = plotter.colored_scatter_matrix(df=iris_df,
colored_column_name="Target")
# fig.savefig("iris-colored_acatter_matrix.png")
plt.show()
return
def setUp(self):
ds = DatasetsTools(datasets.load_iris)
self.iris_df = ds.data_as_df(target_column_name="IrisClass")
self.boton_df = DatasetsTools(datasets.load_boston).data_as_df()
self.tree_clf = DecisionTreeClassifier(max_depth=5,
min_samples_split=10,
min_samples_leaf=10)
self.prd_lbl = "PrdictedIrisClass"
self.actl_lbl = "IrisClass"
self.columns_lst = list(self.iris_df)
self.columns_lst.pop(-1)
self.mu = ModelUtils(df=self.iris_df,
model=self.tree_clf,
columns_lst=self.columns_lst,
predicted_lbl=self.prd_lbl,
actual_lbl=self.actl_lbl)
def test__set_test_df(self):
mu = self.mu
df = mu._set_test_df(None)
iris_df = self.iris_df
self.assertEquals(list(df), list(iris_df))
boton_df = DatasetsTools(datasets.load_boston).data_as_df()
df = mu._set_test_df(boton_df)
self.assertEquals(list(df), list(boton_df))
def main():
iris_dtst = DatasetsTools(datasets.load_iris)
iris_df = iris_dtst.data_as_df()
print(iris_df.info())
# exit()
plotter = DataPlots(df=iris_df, ggplot=True, cmap=cm.jet)
sizes_lst = [(4, 4), (6, 4), (6, 4), (12, 8), (7, 7), (6, 6), (6, 6),
(12, 12)]
tr_axes = []
for i, col in enumerate(list(iris_df)):
ax = plotter.colored_scatter(x=iris_df[col],
y=iris_df.sepal_length_cm,
z2color=iris_df.Target,
figsize=sizes_lst[i])
tr_axes.append(ax)
plt.show()
return
class DatasetsToolsTestCase(unittest.TestCase):
def setUp(self):
self.boston_dtst = DatasetsTools(datasets.load_boston)
self.iris_dtst = DatasetsTools(datasets.load_iris)
def test_boston(self):
self.assertIsInstance(self.boston_dtst, DatasetsTools)
df = self.boston_dtst.data_as_df()
self.assertEqual(list(df.shape), [506, 14])
l = list(df)
headrs = ['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS',
'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT', 'Target']
self.assertEqual(list(df), headrs)
def test_iris(self):
self.assertIsInstance(self.iris_dtst, DatasetsTools)
df = self.iris_dtst.data_as_df()
self.assertEqual(list(df.shape), [150, 5])
headrs = ['sepal_length_cm', 'sepal_width_cm', 'petal_length_cm', 'petal_width_cm', 'Target']
self.assertEqual(list(df), headrs)
def main():
boston_dtst = DatasetsTools(datasets.load_boston)
boston_df = boston_dtst.data_as_df()
print(boston_dtst.info)
plotter = DataPlots(df=boston_df, ggplot=True, cmap=cm.jet)
plotter.colored_scatter_matrix(df=boston_df, colored_column_name="Target")
# plt.show()
iris_dtst = DatasetsTools(datasets.load_iris)
iris_df = iris_dtst.data_as_df()
print(iris_df.info())
plotter = DataPlots(df=iris_df, ggplot=True, cmap=cm.jet)
plotter.colored_scatter_matrix(df=iris_df, colored_column_name="Target")
plt.show()
return
def setUp(self):
self.boston_df = DatasetsTools(datasets.load_boston).data_as_df()
self.iris_df = DatasetsTools(datasets.load_iris).data_as_df()
from matplotlib import pyplot as plt
from sklearn import datasets
from sklearn.tree import DecisionTreeClassifier
from MachineLearningUtils.DatasetTools import DatasetsTools
from MachineLearningUtils.ModelsUtils import ModelUtils
from MachineLearningUtils.UsefulPlots import EvaluationPlots
# load iris data into DataFrame
prd_lbl, actl_lbl = "PrdictedIrisClass", "IrisClass"
iris_df = DatasetsTools(
datasets.load_iris).data_as_df(target_column_name="IrisClass")
# set clf
tree_clf = DecisionTreeClassifier(max_depth=5,
min_samples_split=10,
min_samples_leaf=10)
# simple usage
mu = ModelUtils(df=iris_df,
model=tree_clf,
predicted_lbl=prd_lbl,
actual_lbl=actl_lbl)
mu.split_and_train()
results_df = mu.test_model()
# evaluate results using plot_confusion_matrix
print(mu.confusion_matrix_as_dataframe())
evp = EvaluationPlots(df=results_df,
actual_lbl=actl_lbl,
predicted_lbl=prd_lbl)
def setUp(self):
self.iris_df = DatasetsTools(
datasets.load_iris).data_as_df(target_column_name="target")
self.boston_df = DatasetsTools(datasets.load_boston).data_as_df()
self.fig = plt.figure()
self.iris___BasePlot = _BasePlot(df=self.iris_df)
from matplotlib import pyplot as plt
from sklearn import datasets
import pandas as pd
from sklearn.linear_model import LinearRegression
from MachineLearningUtils.DatasetTools import DatasetsTools
from MachineLearningUtils.LinearModelUtils import LinearModelUtils
from MachineLearningUtils.UsefulPlots import EvaluationPlots
pd.set_option('expand_frame_repr', False)
# load boston data into DataFrame
prd_lbl, target = "PrdictedPrice", "Price"
boston_dtst = DatasetsTools(
datasets.load_boston).data_as_df(target_column_name=target)
print(boston_dtst.describe())
boston_df = boston_dtst.data_as_df(target_column_name=target)
print(boston_df.head())
# set linear model
lm = LinearRegression()
# simple usage
mu = LinearModelUtils(df=boston_df,
lm=lm,
predicted_lbl=prd_lbl,
actual_lbl=target)
mu.split_and_train()
results_df = mu.test_model()
# evaluate results using plot_confusion_matrix
print(mu.get_formula())
evp = EvaluationPlots(df=results_df,
actual_lbl=mu.actual_lbl,
def setUp(self):
self.boston_dtst = DatasetsTools(datasets.load_boston)
self.iris_dtst = DatasetsTools(datasets.load_iris)