def tfidf_cloud(n_trees):
dio = DataIO("/data/Settings_cloud.json")
submission = False
min_samples_split = 2
param = """Normal count vector with max 200. New submission which is repeatable.
and nicer
count_vector_titles = TfidfVectorizer(
read_column(train_filename, column_name),
max_features=200, norm='l1', smooth_idf=True, sublinear_tf=False, use_idf=True)
"""
if submission:
type_n = "train_full"
type_v = "valid_full"
else:
type_n = "train"
type_v = "valid"
#features = dio.join_features("%s_" + type_n + "_tfidf_matrix_max_f_200",
#["Title", "FullDescription", "LocationRaw"],
#extra_features)
#validation_features = dio.join_features("%s_" + type_v + "_tfidf_matrix_max_f_200",
#["Title", "FullDescription", "LocationRaw"],
#extra_valid_features)
#np.save("train_200f_noNorm_categoryTimeType_tfidfl2_features", features)
#np.save("train_200f_noNorm_categoryTimeType_tfidfl2_valid_features", validation_features)
def load(filename):
return joblib.load(path_join("/data", filename))
features = load("train_200f_noNorm_categoryTimeType_tfidfl1_features_jl")
validation_features = load(
"train_200f_noNorm_categoryTimeType_tfidfl1_valid_features_jl")
print "features", features.shape
print "valid features", validation_features.shape
#salaries = dio.get_salaries(type_n, log=True)
#if not submission:
#valid_salaries = dio.get_salaries(type_v, log=True)
#np.save("train_200f_noNorm_categoryTimeType_tfidfl2_salaries", salaries)
#np.save("train_200f_noNorm_categoryTimeType_tfidfl2_valid_salaries", valid_salaries)
#joblib.dump(salaries, "train_200f_noNorm_categoryTimeType_tfidfl2_salaries_jl", compress=5)
#joblib.dump(valid_salaries, "train_200f_noNorm_categoryTimeType_tfidfl2_valid_salaries_jl", compress=5)
#TODO: valid salaries so narobe dumpane
salaries = load("train_200f_noNorm_categoryTimeType_tfidfl2_salaries_jl")
valid_salaries = load(
"train_200f_noNorm_categoryTimeType_tfidfl2_valid_salaries_jl")
dio.is_log = True
print salaries.shape
name = "ExtraTree_min_sample%d_%dtrees_200f_noNorm_categoryTimeType_tfidfl1_new_log" % (
min_samples_split, n_trees)
print name
#dio.save_prediction("testni", np.array([1,2,3]), type_n="testno")
classifier = ExtraTreesRegressor(
n_estimators=n_trees,
verbose=2,
n_jobs=4, # 2 jobs on submission / 4 on valid test
oob_score=False,
min_samples_split=min_samples_split,
random_state=3465343)
#dio.save_model(classifier, "testni_model", 99.)
classifier.fit(features, salaries)
predictions = classifier.predict(validation_features)
if submission:
dio.save_prediction(name, predictions, type_n=type_v)
dio.write_submission(name + ".csv", predictions=predictions)
else:
dio.compare_valid_pred(valid_salaries, predictions)
metric = dio.error_metric
mae = metric(valid_salaries, predictions)
print "MAE validation: ", mae
dio.save_model(classifier, name, mae)
dio.save_prediction(name, predictions, type_n=type_v)
#if bin_n > 4 :
#make_grid_search(MultinomialNB(), {"alpha": [0.01, 0.1, 0.5, 1]}, "multinomialnb" + nm, "Multinomial NB" + par)
#make_grid_search(SGDClassifier(), {'n_iter': [50, 100, 150], 'penalty': ['l2', 'l1']}, "sgd_class" + nm, "SGDClassifier classes" + par)
##make_grid_search(KNeighborsClassifier(), {'n_neighbors': range(4,100,20)}, "kneighbour" + nm, "Kneighbour classes" + par)
#make_grid_search(RandomForestClassifier(random_state=42), {'min_samples_split': [2, 30]}, "randomForest" + nm, "Random Forest" + par)
##make_grid_search(GradientBoostingClassifier(), {'learning_rate': [0.1, 0.5], 'subsample': [1,0.8,0.6], 'n_estimators':[100,150]}, "GBM" + nm, "Gradient Boosting Machines " + par)
bin_n = 4
salaries_enc = encode_salaries(salaries, bin_n)
valid_salaries_enc = encode_salaries(valid_salaries, bin_n)
nm = "_tfidf_titleFullLoc_bin%d" % bin_n
model_name = "randomForest" + nm
par = " classed from 0-11500 then %d classes to 100 000 and to end\n Tfidf of Title full and location Raw" % (bin_n)
classifier = RandomForestClassifier(min_samples_split=2, random_state=42)
classifier.fit(features, salaries_enc)
prediction = classifier.predict(validation_features)
dio.save_prediction(model_name, prediction, "valid_classes")
dio.save_model(classifier, model_name, parameters=par)
print (classification_report(valid_salaries_enc, prediction))
print confusion_matrix(valid_salaries_enc, prediction)
prediction = classifier.predict(features)
dio.save_prediction(model_name, prediction, "train_classes")
print (classification_report(salaries_enc, prediction))
print confusion_matrix(salaries_enc, prediction)
classifier = ExtraTreesRegressor(
n_estimators=n_trees,
#classifier = RandomForestRegressor(n_estimators=n_trees,
verbose=2,
n_jobs=4, # 2 jobs on submission / 4 on valid test
oob_score=True,
min_samples_split=min_samples_split,
random_state=3465343)
classifier.fit(features, salaries)
#classifier = dio.load_model(name)
#predictions = classifier.predict(validation_features)
metric = dio.error_metric
mae = metric(valid_salaries, predictions)
print "MAE validation: ", mae
dio.save_model(classifier, name, mae, parameters=param)
dio.save_prediction(name, predictions, type_n=type_v)
importances = classifier.feature_importances_
std = np.std([tree.feature_importances_ for tree in classifier.estimators_],
axis=0)
indices = np.argsort(importances)[::-1]
f_names = map(lambda x: "Title(%d)" % x, range(1, 201))
f_names.extend(map(lambda x: "Desc(%d)" % x, range(1, 201)))
f_names.extend(map(lambda x: "LocR(%d)" % x, range(1, 201)))
f_names.extend(columns)
num_feat = len(f_names)
# Print the feature ranking
print "Feature ranking:"
for f in xrange(len(indices)):
min_samples_split=min_samples_split,
random_state=3465343)
print features[salaries_idx[0], :].shape
print salaries[salaries_idx].shape
classifier.fit(features[salaries_idx[0], :], salaries[salaries_idx])
predictions_part = classifier.predict(validation_features[valid_idx[0]])
return predictions_part, valid_idx
predictions = np.zeros_like(valid_salaries)
for cur_class_id in range(num_classes + 1):
predictions_part, idx = predict(cur_class_id)
if idx is not None:
predictions[idx] = predictions_part
print "Part MAE: ", metric(valid_salaries[idx], predictions_part)
if submission:
dio.save_prediction(name, predictions, type_n=type_v)
dio.write_submission(name + ".csv", predictions=predictions)
else:
dio.compare_valid_pred(valid_salaries, predictions)
metric = dio.error_metric
mae = metric(valid_salaries, predictions)
print "MAE validation: ", mae
dio.save_model(ExtraTreesRegressor(), name, mae)
dio.save_prediction(name, predictions, type_n=type_v)
#oob_predictions = classifier.oob_prediction_
#mae_oob = mean_absolute_error(salaries, oob_predictions)
#print "MAE OOB: ", mae_oob
#classifier1 = ExtraTreesRegressor(n_estimators=n_trees,
#verbose=1,
#n_jobs=3,
#oob_score=False,
"vowpall_loc5"
]
#model_names = [model2, model4]
#model_names = [model1, model6, model4]
#fit_predict(model2)
#fit_predict(model1)
#fit_predict(model3)
#fit_predict(model5)
#fit_predict(model4, features, salaries, validation_features, type_n="test_subm")
model_name = "predictions_submit_test.txt"
predictions = np.loadtxt(path_join(dio.data_dir, "code", "from_fastml", "optional", model_name))
dio.save_prediction("vowpall_submission", predictions, type_v)
model_name = "predictions_submit_test_loc5.txt"
predictions = np.loadtxt(path_join(dio.data_dir, "code", "from_fastml", "optional", model_name))
dio.save_prediction("vowpall_loc5", predictions, type_v)
all_model_predictions = []
for model_name in model_names:
#fit_predict(model_name, features, salaries, validation_features, type_n="test_subm")
model_predictions = dio.get_prediction(model_name=model_name, type_n="test_full")
if not model_name.endswith("log") and not model_name.startswith("vowpall"):
model_predictions = np.log(model_predictions)
print "modelp", model_predictions.shape
#print "%s\nMAE: %f\n" % (model_name, log_mean_absolute_error(np.log(valid_salaries), model_predictions))
all_model_predictions.append(model_predictions)
predictions = np.vstack(all_model_predictions).T
#make_grid_search(MultinomialNB(), {"alpha": [0.01, 0.1, 0.5, 1]}, "multinomialnb" + nm, "Multinomial NB" + par)
#make_grid_search(SGDClassifier(), {'n_iter': [50, 100, 150], 'penalty': ['l2', 'l1']}, "sgd_class" + nm, "SGDClassifier classes" + par)
##make_grid_search(KNeighborsClassifier(), {'n_neighbors': range(4,100,20)}, "kneighbour" + nm, "Kneighbour classes" + par)
#make_grid_search(RandomForestClassifier(random_state=42), {'min_samples_split': [2, 30]}, "randomForest" + nm, "Random Forest" + par)
##make_grid_search(GradientBoostingClassifier(), {'learning_rate': [0.1, 0.5], 'subsample': [1,0.8,0.6], 'n_estimators':[100,150]}, "GBM" + nm, "Gradient Boosting Machines " + par)
bin_n = 4
salaries_enc = encode_salaries(salaries, bin_n)
valid_salaries_enc = encode_salaries(valid_salaries, bin_n)
nm = "_tfidf_titleFullLoc_bin%d" % bin_n
model_name = "randomForest" + nm
par = " classed from 0-11500 then %d classes to 100 000 and to end\n Tfidf of Title full and location Raw" % (
bin_n)
classifier = RandomForestClassifier(min_samples_split=2, random_state=42)
classifier.fit(features, salaries_enc)
prediction = classifier.predict(validation_features)
dio.save_prediction(model_name, prediction, "valid_classes")
dio.save_model(classifier, model_name, parameters=par)
print(classification_report(valid_salaries_enc, prediction))
print confusion_matrix(valid_salaries_enc, prediction)
prediction = classifier.predict(features)
dio.save_prediction(model_name, prediction, "train_classes")
print(classification_report(salaries_enc, prediction))
print confusion_matrix(salaries_enc, prediction)
def tfidf_cloud(n_trees):
dio = DataIO("/data/Settings_cloud.json")
submission = False
min_samples_split = 2
param = """Normal count vector with max 200. New submission which is repeatable.
and nicer
count_vector_titles = TfidfVectorizer(
read_column(train_filename, column_name),
max_features=200, norm='l1', smooth_idf=True, sublinear_tf=False, use_idf=True)
"""
if submission:
type_n = "train_full"
type_v = "valid_full"
else:
type_n = "train"
type_v = "valid"
#features = dio.join_features("%s_" + type_n + "_tfidf_matrix_max_f_200",
#["Title", "FullDescription", "LocationRaw"],
#extra_features)
#validation_features = dio.join_features("%s_" + type_v + "_tfidf_matrix_max_f_200",
#["Title", "FullDescription", "LocationRaw"],
#extra_valid_features)
#np.save("train_200f_noNorm_categoryTimeType_tfidfl2_features", features)
#np.save("train_200f_noNorm_categoryTimeType_tfidfl2_valid_features", validation_features)
def load(filename):
return joblib.load(path_join("/data", filename))
features = load("train_200f_noNorm_categoryTimeType_tfidfl1_features_jl")
validation_features = load("train_200f_noNorm_categoryTimeType_tfidfl1_valid_features_jl")
print "features", features.shape
print "valid features", validation_features.shape
#salaries = dio.get_salaries(type_n, log=True)
#if not submission:
#valid_salaries = dio.get_salaries(type_v, log=True)
#np.save("train_200f_noNorm_categoryTimeType_tfidfl2_salaries", salaries)
#np.save("train_200f_noNorm_categoryTimeType_tfidfl2_valid_salaries", valid_salaries)
#joblib.dump(salaries, "train_200f_noNorm_categoryTimeType_tfidfl2_salaries_jl", compress=5)
#joblib.dump(valid_salaries, "train_200f_noNorm_categoryTimeType_tfidfl2_valid_salaries_jl", compress=5)
#TODO: valid salaries so narobe dumpane
salaries = load("train_200f_noNorm_categoryTimeType_tfidfl2_salaries_jl")
valid_salaries = load("train_200f_noNorm_categoryTimeType_tfidfl2_valid_salaries_jl")
dio.is_log = True
print salaries.shape
name = "ExtraTree_min_sample%d_%dtrees_200f_noNorm_categoryTimeType_tfidfl1_new_log" % (min_samples_split, n_trees)
print name
#dio.save_prediction("testni", np.array([1,2,3]), type_n="testno")
classifier = ExtraTreesRegressor(n_estimators=n_trees,
verbose=2,
n_jobs=4, # 2 jobs on submission / 4 on valid test
oob_score=False,
min_samples_split=min_samples_split,
random_state=3465343)
#dio.save_model(classifier, "testni_model", 99.)
classifier.fit(features, salaries)
predictions = classifier.predict(validation_features)
if submission:
dio.save_prediction(name, predictions, type_n=type_v)
dio.write_submission(name + ".csv", predictions=predictions)
else:
dio.compare_valid_pred(valid_salaries, predictions)
metric = dio.error_metric
mae = metric(valid_salaries, predictions)
print "MAE validation: ", mae
dio.save_model(classifier, name, mae)
dio.save_prediction(name, predictions, type_n=type_v)
