def get_iris_data(file_in):
"""
Fetch the UCI data set on physical characteristics of Iris species.
"""
data_text = open(file_in, 'r').read()
data_rows = data_text.split('\n')
data_rows = data_rows[0:-2] #last two lines are blank
x_headers = [
'sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'target'
]
cat_variables = ['target']
data_all = [row.split(',') for row in data_rows]
output = pd.DataFrame(data_all, columns=x_headers)
output = helpers.replace_missing_mode(output)
for col in output:
print(col)
if col not in cat_variables:
output[col] = [float(x) for x in output[col]]
output = helpers.one_hot_encode(output, exclude=[])
output = helpers.normalize(output)
return (output)
def get_glass_data(file_in):
"""
Fetch the UCI data set on age of chemical characteristics of glass.
"""
data_text = open(file_in, 'r').read()
data_rows = data_text.split('\n')
data_rows = data_rows[0:-1] #last line is blank
x_headers = [
'id', 'RI', 'Na', 'Mg', 'Al', 'Si', 'K', 'Ca', 'Ba', 'Fe', 'target'
]
cat_variables = ['target']
data_all = [row.split(',') for row in data_rows]
output = pd.DataFrame(data_all, columns=x_headers)
output = helpers.replace_missing_mode(output)
for col in output:
print(col)
if col not in cat_variables:
output[col] = [float(x) for x in output[col]]
output = output.drop(['id'], axis=1)
output = helpers.one_hot_encode(output, exclude=[])
output = helpers.normalize(output)
return (output)
def get_cancer_data(file_in):
"""
Fetch the UCI data set on breast cancer characteristics
"""
data_text = open(file_in, 'r').read()
data_rows = data_text.split('\n')
data_rows = data_rows[0:-1] #last line is blank
x_headers = [
'id', 'clump_thickness', 'unif_cell_size', 'unif_cell_shape',
'marginal_adhesion', 'single_epithelial_cell_size', 'bare_nuclei',
'bland_chrmatin', 'normal_nucleoli', 'mitoses', 'target'
]
cat_variables = ['target']
data_all = [row.split(',') for row in data_rows]
output = pd.DataFrame(data_all, columns=x_headers)
output = output.drop(['id'], axis=1)
output = helpers.replace_missing_mode(output)
for col in output:
if col not in cat_variables:
output[col] = [float(x) for x in output[col]]
output = helpers.one_hot_encode(output, exclude=[])
output = helpers.normalize(output)
return (output)
def get_vote_data(file_in):
"""
Fetch and clean the UCI data set on US Representative vote records
"""
data_text = open(file_in, 'r').read()
data_rows = data_text.split('\n')
data_rows = data_rows[0:-1] #last line is blank
x_headers = [
'target', 'handicapped-infants', 'water-project-cost-sharing',
'adoption-of-the-budget-resolution', 'physician-fee-freeze',
'el-salvador-aid', 'religious-groups-in-schools',
'anti-satellite-test-ban', 'aid-to-nicaraguan-contras', 'mx-missile',
'immigration', 'synfuels-corporation-cutback', 'education-spending',
'superfund-right-to-sue', 'crime', 'duty-free-exports',
'export-administration-act-south-africa'
]
cat_variables = ['target']
data_all = [row.split(',') for row in data_rows]
output = pd.DataFrame(data_all, columns=x_headers)
output = helpers.replace_missing_mode(output)
output = helpers.one_hot_encode(output, exclude=[])
output = helpers.normalize(output)
return (output)
def get_soy_data(file_in):
"""
Fetch the UCI data set on diseases of soybean samples.
"""
data_text = open(file_in, 'r').read()
data_rows = data_text.split('\n')
data_rows = data_rows[0:-1] #last line is blank
x_headers = [
'date', 'plant-stand', 'precip', 'temp', 'hail', 'crop-hist',
'area-damaged', 'severity', 'seed-tmt', 'germination', 'plant-growth',
'leaves', 'leafspots-halo', 'leafspots-marg', 'leafspot-size',
'leaf-shread', 'leaf-malf', 'leaf-mild', 'stem', 'lodging',
'stem-cankers', 'canker-lesion', 'fruiting-bodies', 'external decay',
'mycelium', 'int-discolor', 'sclerotia', 'fruit-pods', 'fruit spots',
'seed', 'mold-growth', 'seed-discolor', 'seed-size', 'shriveling',
'roots', 'target'
]
cat_variables = ['target']
data_all = [row.split(',') for row in data_rows]
output = pd.DataFrame(data_all, columns=x_headers)
output = helpers.replace_missing_mode(output)
output = helpers.one_hot_encode(output, exclude=[])
output = helpers.normalize(output)
return (output)