def run_csv(fin, uid_feature, label_feature, clfs=DBG_std_clfs):
""" Turn a CSV into an Experiment then turn the Experiment into models"""
sa = open_csv_as_sa(fin)
labels = sa[label_feature]
M = remove_cols(sa, label_feature)
exp = Experiment(M, labels, clfs=clfs)
register_exp(exp, uid_feature)
def run_csv(fin, uid_feature, label_feature):
sa = open_csv_as_sa(fin)
labels = sa[label_feature]
M = remove_cols(sa, label_feature)
exp = Experiment(M, labels, clfs=DBG_std_clfs)
exp.run()
last_experiments[current_user.id] = exp
clear_models(current_user.id)
for trial in exp.trials:
for subset in trial.runs:
for run in subset:
register_model(current_user.id, run.clf, dt.now(),
run.M[run.train_indices],
run.M[run.test_indices],
run.labels[run.train_indices],
run.labels[run.test_indices], run.col_names,
uid_feature)
def run_csv(fin, uid_feature, label_feature):
sa = open_csv_as_sa(fin)
labels = sa[label_feature]
M = remove_cols(sa, label_feature)
exp = Experiment(M, labels, clfs=DBG_std_clfs)
exp.run()
last_experiments[current_user.id] = exp
clear_models(current_user.id)
for trial in exp.trials:
for subset in trial.runs:
for run in subset:
register_model(
current_user.id,
run.clf,
dt.now(),
run.M[run.train_indices],
run.M[run.test_indices],
run.labels[run.train_indices],
run.labels[run.test_indices],
run.col_names,
uid_feature)
plot_kernel_density,
plot_box_plot)
from diogenes.grid_search import Experiment
from diogenes.grid_search import std_clfs as std_clfs
from diogenes.utils import remove_cols
data = open_csv_url(
'http://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-white.csv',
delimiter=';')
y = data['quality']
M = remove_cols(data, 'quality')
y = y < np.average(y)
if False:
for x in describe_cols(M):
print x
if False:
plot_correlation_scatter_plot(M)
plot_correlation_matrix(M)
plot_kernel_density(M['f0']) #no designation of col name
plot_box_plot(M['f0']) #no designation of col name
exp = Experiment(M, y, clfs=std_clfs)
exp.make_csv()
from diogenes.read import open_csv_url
from diogenes.display import (plot_correlation_scatter_plot,
plot_correlation_matrix, plot_kernel_density,
plot_box_plot)
from diogenes.grid_search import Experiment
from diogenes.grid_search import std_clfs as std_clfs
from diogenes.utils import remove_cols
data = open_csv_url(
'http://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-white.csv',
delimiter=';')
y = data['quality']
M = remove_cols(data, 'quality')
y = y < np.average(y)
if False:
for x in describe_cols(M):
print x
if False:
plot_correlation_scatter_plot(M)
plot_correlation_matrix(M)
plot_kernel_density(M['f0']) #no designation of col name
plot_box_plot(M['f0']) #no designation of col name
exp = Experiment(M, y, clfs=std_clfs)
exp.make_csv()