liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-12 15:26:54 +08:00
Code Activity

Merge branch 'main' of https://github.com/you-n-g/qlib into main

Browse Source
This commit is contained in:
Alex Wang
2020-11-26 22:28:57 +08:00
parent e25fc3b243 dae28139da
commit 293c405593
13 changed files with 116 additions and 114 deletions
Download Patch File Download Diff File Expand all files Collapse all files

66
qlib/contrib/model/pytorch_gats.py
View File

@@ -9,10 +9,8 @@ import os
import numpy as np
import pandas as pd
import copy
from sklearn.metrics import roc_auc_score, mean_squared_error
import logging
from ...utils import unpack_archive_with_buffer, save_multiple_parts_file, create_save_path, drop_nan_by_y_index
from ...log import get_module_logger, TimeInspector
from ...utils import create_save_path
from ...log import get_module_logger
import torch
import torch.nn as nn
@@ -49,7 +47,6 @@ class GAT(Model):
n_epochs=200,
lr=0.001,
metric="IC",
batch_size=2000,
early_stop=20,
loss="mse",
base_model="GRU",
@@ -71,7 +68,6 @@ class GAT(Model):
self.n_epochs = n_epochs
self.lr = lr
self.metric = metric
self.batch_size = batch_size
self.early_stop = early_stop
self.optimizer = optimizer.lower()
self.loss = loss
@@ -90,7 +86,6 @@ class GAT(Model):
"\nn_epochs : {}"
"\nlr : {}"
"\nmetric : {}"
"\nbatch_size : {}"
"\nearly_stop : {}"
"\noptimizer : {}"
"\nloss_type : {}"
@@ -106,7 +101,6 @@ class GAT(Model):
n_epochs,
lr,
metric,
batch_size,
early_stop,
optimizer.lower(),
loss,
@@ -165,23 +159,31 @@ class GAT(Model):
def cal_ic(self, pred, label):
return torch.mean(pred * label)
def get_daily_inter(self, df, shuffle=False):
# organize the train data into daily inter as daily batches
daily_count = df.groupby(level=0).size().values
daily_index = np.roll(np.cumsum(daily_count), 1)
daily_index[0] = 0
if shuffle:
# shuffle the daily inter data
daily_shuffle = list(zip(daily_index, daily_count))
np.random.shuffle(daily_shuffle)
daily_index, daily_count = zip(*daily_shuffle)
return daily_index, daily_count
def train_epoch(self, x_train, y_train):
x_train_values = x_train.values
y_train_values = np.squeeze(y_train.values) * 100
self.GAT_model.train()
indices = np.arange(len(x_train_values))
np.random.shuffle(indices)
# organize the train data into daily inter as daily batches
daily_index, daily_count = self.get_daily_inter(x_train, shuffle=True)
for i in range(len(indices))[:: self.batch_size]:
if len(indices) - i < self.batch_size:
break
feature = torch.from_numpy(x_train_values[indices[i : i + self.batch_size]]).float()
label = torch.from_numpy(y_train_values[indices[i : i + self.batch_size]]).float()
for idx, count in zip(daily_index, daily_count):
batch = slice(idx, idx + count)
feature = torch.from_numpy(x_train_values[batch]).float()
label = torch.from_numpy(y_train_values[batch]).float()
if self.use_gpu:
feature = feature.cuda()
@@ -206,15 +208,13 @@ class GAT(Model):
scores = []
losses = []
indices = np.arange(len(x_values))
# organize the test data into daily inter as daily batches
daily_index, daily_count = self.get_daily_inter(data_x, shuffle=False)
for i in range(len(indices))[:: self.batch_size]:
if len(indices) - i < self.batch_size:
break
feature = torch.from_numpy(x_values[indices[i : i + self.batch_size]]).float()
label = torch.from_numpy(y_values[indices[i : i + self.batch_size]]).float()
for idx, count in zip(daily_index, daily_count):
batch = slice(idx, idx + count)
feature = torch.from_numpy(x_values[batch]).float()
label = torch.from_numpy(y_values[batch]).float()
if self.use_gpu:
feature = feature.cuda()
@@ -247,7 +247,6 @@ class GAT(Model):
if save_path == None:
save_path = create_save_path(save_path)
stop_steps = 0
train_loss = 0
best_score = -np.inf
best_epoch = 0
evals_result["train"] = []
@@ -314,17 +313,14 @@ class GAT(Model):
index = x_test.index
self.GAT_model.eval()
x_values = x_test.values
sample_num = x_values.shape[0]
preds = []
for begin in range(sample_num)[:: self.batch_size]:
# organize the data into daily inter as daily batches
daily_index, daily_count = self.get_daily_inter(x_test, shuffle=False)
if sample_num - begin < self.batch_size:
end = sample_num
else:
end = begin + self.batch_size
x_batch = torch.from_numpy(x_values[begin:end]).float()
for idx, count in zip(daily_index, daily_count):
batch = slice(idx, idx + count)
x_batch = torch.from_numpy(x_values[batch]).float()
if self.use_gpu:
x_batch = x_batch.cuda()

10
qlib/contrib/model/pytorch_gru.py
View File

@@ -46,7 +46,7 @@ class GRU(Model):
dropout=0.0,
n_epochs=200,
lr=0.001,
metric="IC",
metric="",
batch_size=2000,
early_stop=20,
loss="mse",
@@ -140,21 +140,16 @@ class GRU(Model):
def metric_fn(self, pred, label):
mask = torch.isfinite(label)
if self.metric == "IC":
return self.cal_ic(pred[mask], label[mask])
if self.metric == "" or self.metric == "loss": # use loss
return -self.loss_fn(pred[mask], label[mask])
raise ValueError("unknown metric `%s`" % self.metric)
def cal_ic(self, pred, label):
return torch.mean(pred * label)
def train_epoch(self, x_train, y_train):
x_train_values = x_train.values
y_train_values = np.squeeze(y_train.values) * 100
y_train_values = np.squeeze(y_train.values)
self.gru_model.train()
@@ -193,7 +188,6 @@ class GRU(Model):
losses = []
indices = np.arange(len(x_values))
np.random.shuffle(indices)
for i in range(len(indices))[:: self.batch_size]:

57
qlib/contrib/model/pytorch_hats.py
View File

@@ -54,7 +54,6 @@ class HATS(Model):
n_epochs=200,
lr=0.01,
metric="IC",
batch_size=800,
early_stop=20,
loss="mse",
base_model="GRU",
@@ -76,7 +75,6 @@ class HATS(Model):
self.n_epochs = n_epochs
self.lr = lr
self.metric = metric
self.batch_size = batch_size
self.early_stop = early_stop
self.optimizer = optimizer.lower()
self.loss = loss
@@ -95,7 +93,6 @@ class HATS(Model):
"\nn_epochs : {}"
"\nlr : {}"
"\nmetric : {}"
"\nbatch_size : {}"
"\nearly_stop : {}"
"\noptimizer : {}"
"\nloss_type : {}"
@@ -111,7 +108,6 @@ class HATS(Model):
n_epochs,
lr,
metric,
batch_size,
early_stop,
optimizer.lower(),
loss,
@@ -169,6 +165,18 @@ class HATS(Model):
def cal_ic(self, pred, label):
return torch.mean(pred * label)
def get_daily_inter(self, df, shuffle=False):
# organize the train data into daily inter as daily batches
daily_count = df.groupby(level=0).size().values
daily_index = np.roll(np.cumsum(daily_count), 1)
daily_index[0] = 0
if shuffle:
# shuffle the daily inter data
daily_shuffle = list(zip(daily_index, daily_count))
np.random.shuffle(daily_shuffle)
daily_index, daily_count = zip(*daily_shuffle)
return daily_index, daily_count
def train_epoch(self, x_train, y_train):
x_train_values = x_train.values
@@ -176,16 +184,13 @@ class HATS(Model):
self.HATS_model.train()
indices = np.arange(len(x_train_values))
np.random.shuffle(indices)
# organize the train data into daily inter as daily batches
daily_index, daily_count = self.get_daily_inter(x_train, shuffle=True)
for i in range(len(indices))[:: self.batch_size]:
if len(indices) - i < self.batch_size:
break
feature = torch.from_numpy(x_train_values[indices[i : i + self.batch_size]]).float()
label = torch.from_numpy(y_train_values[indices[i : i + self.batch_size]]).float()
for idx, count in zip(daily_index, daily_count):
batch = slice(idx, idx + count)
feature = torch.from_numpy(x_train_values[batch]).float()
label = torch.from_numpy(y_train_values[batch]).float()
if self.use_gpu:
feature = feature.cuda()
@@ -210,15 +215,13 @@ class HATS(Model):
scores = []
losses = []
indices = np.arange(len(x_values))
# organize the test data into daily inter as daily batches
daily_index, daily_count = self.get_daily_inter(data_x, shuffle=False)
for i in range(len(indices))[:: self.batch_size]:
if len(indices) - i < self.batch_size:
break
feature = torch.from_numpy(x_values[indices[i : i + self.batch_size]]).float()
label = torch.from_numpy(y_values[indices[i : i + self.batch_size]]).float()
for idx, count in zip(daily_index, daily_count):
batch = slice(idx, idx + count)
feature = torch.from_numpy(x_values[batch]).float()
label = torch.from_numpy(y_values[batch]).float()
if self.use_gpu:
feature = feature.cuda()
@@ -319,14 +322,12 @@ class HATS(Model):
sample_num = x_values.shape[0]
preds = []
for begin in range(sample_num)[:: self.batch_size]:
# organize the data into daily inter as daily batches
daily_index, daily_count = self.get_daily_inter(x_test, shuffle=False)
if sample_num - begin < self.batch_size:
end = sample_num
else:
end = begin + self.batch_size
x_batch = torch.from_numpy(x_values[begin:end]).float()
for idx, count in zip(daily_index, daily_count):
batch = slice(idx, idx + count)
x_batch = torch.from_numpy(x_values[batch]).float()
if self.use_gpu:
x_batch = x_batch.cuda()