def train_model(item_type):
model_dir = "models/" + item_type.lower().replace(" ", "_")
if os.path.exists(model_dir):
return
print("==> Training model for '%s'" % item_type)
csv_filename = filename = "data/" + item_type.lower().replace(" ", "_") + ".csv"
df_all = pd.read_csv(csv_filename, skipinitialspace=True, encoding='utf-8')
df_all.fillna(0.0, inplace=True)
# Convert the price to a bucket representing a range
df_all['price_chaos'] = (df_all['price_chaos'].apply(util.price_bucket)).astype(int)
# Hash the item type to a number
df_all['itemType'] = (df_all['itemType'].apply(lambda x: util.type_hash[x])).astype(float)
LABEL_COLUMN = util.LABEL_COLUMN
# Split the data 80/20 training/test
percent_test = 20
n = (len(df_all) * percent_test)/100
df_train = df_all.head(len(df_all) - n)
df_test = df_all.tail(n)
train_x = df_train.ix[:, df_train.columns != LABEL_COLUMN].as_matrix().astype(float)
train_y = df_train.as_matrix([LABEL_COLUMN])
test_x = df_test.ix[:, df_test.columns != LABEL_COLUMN].as_matrix().astype(float)
test_y = df_test.as_matrix([LABEL_COLUMN])
deep_columns = tf.contrib.learn.infer_real_valued_columns_from_input(train_x)
hidden_units = util.get_hidden_units(len(df_train.columns)-1)
model = DNNClassifier(model_dir=model_dir, feature_columns=deep_columns, hidden_units=hidden_units,
n_classes=len(util.bins), enable_centered_bias=True)
steps = len(df_train)/75
sessions = (steps/500)+2
for i in range(sessions):
model.fit(train_x, train_y, steps=500, batch_size=5000)
results = model.evaluate(test_x, test_y, steps=1, batch_size=df_test.size)
# Print some predictions from the test data
predictions = df_test.sample(10)
v = model.predict_proba(predictions.ix[:, df_test.columns != LABEL_COLUMN].as_matrix().astype(float), batch_size=10)
price_map = []
for i in v:
# take the top 5 most likely price ranges
top_largest = i.argsort()[-5:][::-1]
prices = {}
for p in top_largest:
prices[util.get_bin_label(p)] = float(round(100*i[p], 1))
price_map.append(prices)
for r in price_map:
print r
type=str)
parse = parser.parse_args()
TRAIN_DATASET = parse.train
TEST_DATASET = parse.test
OUTPUT_PATH = parse.output
np.random.seed(19260817)
train_set = pandas.read_csv(TRAIN_DATASET)
test_set = pandas.read_csv(TEST_DATASET)
encoder = LabelEncoder().fit(train_set["species"])
train = train_set.drop(["species", "id"], axis=1).values
label = encoder.transform(train_set["species"])
test = test_set.drop(["id"], axis=1).values
scaler = StandardScaler().fit(train)
train = scaler.transform(train)
scaler = StandardScaler().fit(test)
test = scaler.transform(test)
feature_columns = [real_valued_column("", dimension=192)]
classifier = DNNClassifier(feature_columns=feature_columns,
n_classes=99,
hidden_units=[1024, 512, 256],
optimizer=tf.train.AdamOptimizer)
classifier.fit(x=train, y=label, steps=1000)
output = classifier.predict(test)
output_prob = classifier.predict_proba(test)
test_id = test_set.pop("id")
result = pandas.DataFrame(output_prob,
index=test_id,
columns=encoder.classes_)
result.to_csv(OUTPUT_PATH)