def train_model(X, y, X_, y_, clf):
model = utils.find_best_estimator(clf, X, y, section="approach2")
preds = model.predict_proba(X_)
log_loss = metrics.log_loss(y_, preds)
return model, log_loss
df_all.shape[1])
# Separating the train and test
train = df_all[df_all["ID"].isin(id_train)]
test = df_all[df_all["ID"].isin(id_test)]
logger.info("Training model. Train dataset shape : %s" % str(train.shape))
X, X_eval, y, y_eval = cv.train_test_split(train, target, test_size=0.4)
preds = None
clf = ensemble.RandomForestClassifier()
clf.set_params(**cfg[section]["best_estimator"])
if cfg[section]["find_best"] == True:
model = utils.find_best_estimator(clf,
X,
y,
cfg,
section=section,
grid_search_params_key="param_dist",
scoring="f1",
verbosity=2)
else:
model = clf.fit(X, y)
preds = model.predict_proba(X_eval)[:, 1]
log_loss = metrics.log_loss(y_eval, preds)
logger.info("Trained model %s" % model)
logger.info("Log loss : %.6f" % log_loss)
logger.info("Making predictions..")
predicted_probabilities = model.predict_proba(test)[:, 1]
utils.make_submission_file(predicted_probabilities, "simple-randomforest")
num_classes = len(label_encoder.classes_)
y = label_encoder.transform(target)
# Level 0 classifiers
clfs = [
ExtraTreesClassifier(**utils.read_estimator_params(s, "et")),
LogisticRegression(**utils.read_estimator_params(s, "lr")),
RandomForestClassifier(**utils.read_estimator_params(s, "rf"))
]
# First, run grid search (if enabled) to find the best estimator
results_1 = []
for clf in clfs:
ts = time.time()
clf_name = type(clf).__name__
model = utils.find_best_estimator(clf, X_train, y_train, section=s)
preds = model.predict_proba(X_valid)
log_loss = metrics.log_loss(y_valid, preds)
results_1.append((utils.get_key(clf_name), model, log_loss))
logger.info("Trained {} in {:.2f} seconds, Log loss : {:.6f}"
.format(clf_name, (time.time() - ts), log_loss))
# Sort by log_loss
results_1.sort(key=lambda tup: tup[2])
logger.info(tabulate(zip([r[0] for r in results_1],
[r[2] for r in results_1]),
floatfmt=".4f", headers=("model", "log_loss")))
clfs = [clf[1] for clf in results_1] # required for blending stage
# Next, run stacked generalization (blending)
logger.info("Start blending")
results_2 = []
# Drop the remaining categorical columns (ones we did not convert)
col_names = list(df_all.columns.values)
logger.info("Categorical columns not converted : %s" % remaining_cols)
df_all = df_all.drop(remaining_cols, axis=1)
logger.info("%d columns after dropping remaining categorical columns." %
df_all.shape[1])
# Separating the train and test
train = df_all[df_all["ID"].isin(id_train)]
test = df_all[df_all["ID"].isin(id_test)]
logger.info("Training model. Train dataset shape : %s" % str(train.shape))
X, X_eval, y, y_eval = cv.train_test_split(train, target, test_size=0.4)
preds = None
clf = ensemble.RandomForestClassifier()
clf.set_params(**cfg[section]["best_estimator"])
if cfg[section]["find_best"] == True:
model = utils.find_best_estimator(clf, X, y, cfg, section=section,
grid_search_params_key="param_dist",
scoring="f1", verbosity=2)
else:
model = clf.fit(X, y)
preds = model.predict_proba(X_eval)[:, 1]
log_loss = metrics.log_loss(y_eval, preds)
logger.info("Trained model %s" % model)
logger.info("Log loss : %.6f" % log_loss)
logger.info("Making predictions..")
predicted_probabilities = model.predict_proba(test)[:, 1]
utils.make_submission_file(predicted_probabilities, "simple-randomforest")
# For numeric columns, replace missing values with -999
tmp_len = len(train[a_vals.isnull()])
if tmp_len > 0:
train.loc[a_vals.isnull(), a] = -999
tmp_len = len(test[b_vals.isnull()])
if tmp_len > 0:
test.loc[b_vals.isnull(), b] = -999
# Training
t0 = time.time()
clf = ExtraTreesClassifier()
clf.set_params(**cfg[s]["estimator_params_etc"])
X, X_eval, y, y_eval = cv.train_test_split(train, target, test_size=0.4)
if cfg[s]["find_best"] == True:
model = utils.find_best_estimator(clf, X, y, cfg, section=s,
grid_search_params_key="gs_params_etc",
scoring="log_loss", verbosity=2)
logger.info(model)
else:
model = clf.fit(X, y)
logger.info("%.2f seconds to train %s" % ((time.time() - t0), model))
preds = model.predict_proba(X_eval)[:, 1]
log_loss = metrics.log_loss(y_eval, preds)
logger.info("Log loss : %.6f" % log_loss)
logger.info("Making predictions..")
y_pred = model.predict_proba(test)
utils.make_submission_file(y_pred[:, 1], "etc_")
tmp_len = len(test[b_vals.isnull()])
if tmp_len > 0:
test.loc[b_vals.isnull(), b] = -999
# Training
t0 = time.time()
clf = ExtraTreesClassifier()
clf.set_params(**cfg[s]["estimator_params_etc"])
X, X_eval, y, y_eval = cv.train_test_split(train, target, test_size=0.4)
if cfg[s]["find_best"] == True:
model = utils.find_best_estimator(
clf,
X,
y,
cfg,
section=s,
grid_search_params_key="gs_params_etc",
scoring="log_loss",
verbosity=2)
logger.info(model)
else:
model = clf.fit(X, y)
logger.info("%.2f seconds to train %s" % ((time.time() - t0), model))
preds = model.predict_proba(X_eval)[:, 1]
log_loss = metrics.log_loss(y_eval, preds)
logger.info("Log loss : %.6f" % log_loss)
logger.info("Making predictions..")
y_pred = model.predict_proba(test)
