def test_dirty_float_target_regression():
titanic_data = load_titanic()
data = pd.DataFrame({'one': np.repeat(np.arange(50), 2)})
dirty = make_dirty_float()
data['target'] = dirty
with pytest.warns(UserWarning, match="Discarding dirty_float targets that "
"cannot be converted to float."):
clean(data, target_col="target")
with pytest.warns(UserWarning, match="Discarding dirty_float targets that "
"cannot be converted to float."):
plot(data, target_col="target")
# check if works for non dirty_float targets
plot(titanic_data, 'survived')
""" Adult Census Dataset Visualization ==================================== """ # sphinx_gallery_thumbnail_number = 2 from dabl import plot from dabl.datasets import load_adult import matplotlib.pyplot as plt # load the adult census housing dataset # returns a plain dataframe data = load_adult() plot(data, 'income', scatter_alpha=.1) plt.show()
"""
Diamonds Dataset Visualization
==========================================
Regression on the classical diamond dataset.
"""
# sphinx_gallery_thumbnail_number = 2
import matplotlib.pyplot as plt
from sklearn.datasets import fetch_openml
from dabl import plot
X, y = fetch_openml('diamonds', as_frame=True, return_X_y=True)
plot(X, y)
plt.show()
# In[ ]:
import dabl
# In[ ]:
feature_df = bdf[final_feature_list]
# In[ ]:
dabl_data = dabl.clean(feature_df)
# In[ ]:
dabl.plot(dabl_data, target_col='save_within_48')
# In[ ]:
X = dabl_data.drop("save_within_48", axis=1)
Y = dabl_data.save_within_48
# In[ ]:
preprocessor = dabl.EasyPreprocessor()
X_trans = preprocessor.fit_transform(X)
# In[ ]:
fc = dabl.SimpleClassifier(random_state=0).fit(X_trans, Y)
""" Ames Housing Dataset Visualization ==================================== """ from dabl import plot from dabl.datasets import load_ames import matplotlib.pyplot as plt # load the ames housing dataset # returns a plain dataframe data = load_ames() plot(data, 'SalePrice') plt.show()
# No. of unique items present in the categorical column
data.select_dtypes('object').nunique()
# Percentage of missing data in each columns present in the data
no_of_columns = data.shape[0]
percentage_of_missing_data = data.isnull().sum()/no_of_columns
print(percentage_of_missing_data)
# comparison of all other attributes with respect to Math Marks
plt.rcParams['figure.figsize'] = (18, 6)
plt.style.use('fivethirtyeight')
dabl.plot(data, target_col = 'math score')
# comparison of all other attributes with respect to Reading Marks
plt.rcParams['figure.figsize'] = (18, 6)
plt.style.use('fivethirtyeight')
dabl.plot(data, target_col = 'reading score')
# comparison of all other attributes with respect to Writing Marks
plt.rcParams['figure.figsize'] = (18, 6)
plt.style.use('fivethirtyeight')
dabl.plot(data, target_col = 'writing score')
# Inferential Statistics
# print data(feature)shape
wine.data.shape
# print the wine data features (top 5 records)
print (wine.data[0:5])
print (wine.target)
#Count number of observation in each class
for i in set(wine.target):
print('Class', i, ' -> ', list(wine.target).count(i))
explore()
# Import Gaussian Naive Bayes model
from sklearn.naive_bayes import GaussianNB as GNB
# Train the model using the training sets
# and Predict the response for test dataset
y_pred = GNB().fit(X_train, y_train).predict(X_test)
# Import scikit-learn metrics module for accuracy calculation
from sklearn import metrics
# Model Accuracy, how often is the classifier correct?
print(f"Accuracy: {100*metrics.accuracy_score(y_test, y_pred):.3f}%")
import matplotlib.pyplot as plt
from dabl import plot
from dabl.utils import data_df_from_bunch
plot(data_df_from_bunch(wine), 'target')
plt.show()
""" Wine Classification Dataset Visualization ========================================== """ import matplotlib.pyplot as plt from sklearn.datasets import load_wine from dabl import plot from dabl.utils import data_df_from_bunch wine_bunch = load_wine() wine_df = data_df_from_bunch(wine_bunch) plot(wine_df, 'target') plt.show()
