def transform_datetime(df: pd.DataFrame, config: Config):
date_parts = ["year", "weekday", "month", "day", "hour"]
if "date_columns" not in config:
config["date_columns"] = {}
for c in [c for c in df if c.startswith("datetime_")]:
config["date_columns"][c] = []
for part in date_parts:
part_col = c + "_" + part
df[part_col] = getattr(df[c].dt, part).astype(np.uint16 if part == "year" else np.uint8).values
if not (df[part_col] != df[part_col].iloc[0]).any():
Log.print(part_col + " is constant")
df.drop(part_col, axis=1, inplace=True)
else:
config["date_columns"][c].append(part)
df.drop(c, axis=1, inplace=True)
else:
for c, parts in config["date_columns"].items():
for part in parts:
part_col = c + "_" + part
df[part_col] = getattr(df[c].dt, part)
df.drop(c, axis=1, inplace=True)
def transform_categorical(df: pd.DataFrame, config: Config):
if "categorical_columns" not in config:
config["categorical_columns"] = []
# https://www.kaggle.com/ogrellier/python-target-encoding-for-categorical-features
prior = config["categorical_prior"] = df["target"].mean()
min_samples_leaf = 10
smoothing = 5
config["categorical_columns_string"] = {}
for c in [c for c in df if c.startswith("string_")]:
Log.print(c)
config["categorical_columns"].append(c)
averages = df[[c, "target"]].groupby(c)["target"].agg(["mean", "count"])
smooth = 1 / (1 + np.exp(-(averages["count"] - min_samples_leaf) / smoothing))
averages["target"] = prior * (1 - smooth) + averages["mean"] * smooth
config["categorical_columns_string"][c] = averages["target"].to_dict()
config["categorical_columns_id"] = {}
for c in [c for c in df if c.startswith("id_")]:
Log.print(c)
config["categorical_columns"].append(c)
if df[c].dtype == str or df[c].dtype == object:
config["categorical_columns_id"][c] = {v: i for i, v in enumerate(df[c].unique())}
for c, values in config["categorical_columns_string"].items():
df.loc[:, c] = df[c].apply(lambda x: values[x] if x in values else config["categorical_prior"])
for c, values in config["categorical_columns_id"].items():
df.loc[:, c] = df[c].apply(lambda x: values[x] if x in values else -1)
def train_lightgbm(X: pd.DataFrame, y: pd.Series, config: Config):
params = {
"objective": "regression" if config.is_regression() else "binary",
"metric": "rmse" if config.is_regression() else "auc",
"verbosity": -1,
"seed": 1,
}
X_sample, y_sample = data_sample(X, y, config, nrows=20000)
hyperparams = hyperopt_lightgbm(X_sample, y_sample, params, config)
X_train, X_val, y_train, y_val = data_split(X, y, config)
config["model"] = lgb.train(
{**params, **hyperparams},
lgb.Dataset(X_train, label=y_train),
5000,
lgb.Dataset(X_val, label=y_val),
early_stopping_rounds=100,
verbose_eval=100,
)
config.save()
try:
with time_limit(config.time_left() - 10):
config["model"] = lgb.train(
{**params, **hyperparams},
lgb.Dataset(X, label=y),
int(1.2 * config["model"].best_iteration),
)
except TimeoutException:
Log.print("Timed out!")
def drop_constant_columns(df: pd.DataFrame, config: Config):
if "constant_columns" not in config:
config["constant_columns"] = [c for c in df if c.startswith("number_") and not (df[c] != df[c].iloc[0]).any()]
Log.print("Constant columns: {}".format(config["constant_columns"]))
if len(config["constant_columns"]) > 0:
df.drop(config["constant_columns"], axis=1, inplace=True)
def validate_dataset(alias: str, mode: str, train_limit: int) -> np.float64:
Log.print(alias)
automl = AutoML("models/check_{}".format(alias))
automl.config["time_limit"] = train_limit
automl.train("data/check_{}/train.csv".format(alias), mode)
automl.config["time_limit"] = 300
automl.config["start_time"] = time.time()
_, score = automl.predict("data/check_{}/test.csv".format(alias), "predictions/check_{}.csv".format(alias))
return score
def subsample(df: pd.DataFrame, config: Config, max_size_mb: float=2.0):
if config.is_train():
df_size_mb = df.memory_usage(deep=True).sum() / 1024 / 1024
if df_size_mb > max_size_mb:
mem_per_row = df_size_mb / len(df)
sample_rows = int(max_size_mb / mem_per_row)
Log.print("Size limit exceeded: {:0.2f} Mb. Dataset rows: {}. Subsample to {} rows.".format(df_size_mb, len(df), sample_rows))
_, df_drop = train_test_split(df, train_size=sample_rows, random_state=1)
df.drop(df_drop.index, inplace=True)
config["nrows"] = sample_rows
else:
config["nrows"] = len(df)
def to_int8(df: pd.DataFrame, config: Config):
if "int8_columns" not in config:
config["int8_columns"] = []
vals = [-1, 0, 1]
for c in [c for c in df if c.startswith("number_")]:
if (~df[c].isin(vals)).any():
continue
config["int8_columns"].append(c)
Log.print("Num columns: {}".format(len(config["int8_columns"])))
if len(config["int8_columns"]) > 0:
df.loc[:, config["int8_columns"]] = df.loc[:, config["int8_columns"]].astype(np.int8)
def objective(hyperparams):
if config.is_time_fraction_limit():
score = np.inf if config.is_regression() else 0
return {'loss': score, 'status': STATUS_OK}
model = lgb.train({**params, **hyperparams}, train_data, 300, valid_data,
early_stopping_rounds=100, verbose_eval=False)
score = model.best_score["valid_0"][params["metric"]]
Log.print(score)
if config.is_classification():
score = -score
return {'loss': score, 'status': STATUS_OK}
def hyperopt_lightgbm(X: pd.DataFrame, y: pd.Series, params: Dict, config: Config):
X_train, X_val, y_train, y_val = data_split(X, y, config, test_size=0.5)
train_data = lgb.Dataset(X_train, label=y_train)
valid_data = lgb.Dataset(X_val, label=y_val)
space = {
"learning_rate": hp.choice("learning_rate", np.arange(0.01, 0.05, 0.01)),
"boost_from_average": hp.choice("boost_from_average", [True, False]),
"is_unbalance": hp.choice("is_unbalance", [True, False]),
"zero_as_missing": hp.choice("zero_as_missing", [True, False]),
"max_depth": hp.choice("max_depth", [-1, 2, 3, 4, 5, 6, 7]),
"num_leaves": hp.choice("num_leaves", [11, 31, 51, 101, 151, 201]),
"feature_fraction": hp.choice("feature_fraction", np.arange(0.5, 1.0, 0.1)),
"bagging_fraction": hp.choice("bagging_fraction", np.arange(0.5, 1.0, 0.1)),
"bagging_freq": hp.choice("bagging_freq", [1, 3, 5, 10, 20, 50]),
"reg_alpha": hp.uniform("reg_alpha", 0, 10),
"reg_lambda": hp.uniform("reg_lambda", 0, 10),
"min_child_weight": hp.uniform("min_child_weight", 0, 10),
}
config.limit_time_fraction(0.15)
def objective(hyperparams):
if config.is_time_fraction_limit():
score = np.inf if config.is_regression() else 0
return {'loss': score, 'status': STATUS_OK}
model = lgb.train({**params, **hyperparams}, train_data, 300, valid_data,
early_stopping_rounds=100, verbose_eval=False)
score = model.best_score["valid_0"][params["metric"]]
Log.print(score)
if config.is_classification():
score = -score
return {'loss': score, 'status': STATUS_OK}
trials = Trials()
best = hyperopt.fmin(fn=objective, space=space, trials=trials, algo=tpe.suggest, max_evals=100, verbose=1,
rstate= np.random.RandomState(1))
hyperparams = space_eval(space, best)
Log.print("{:0.4f} {}".format(trials.best_trial['result']['loss'], hyperparams))
return hyperparams
def feature_selection(df: pd.DataFrame, config: Config):
if config.is_train():
df_size_mb = df.memory_usage(deep=True).sum() / 1024 / 1024
if df_size_mb < 2 * 1024:
return
selected_columns = []
config_sample = copy.deepcopy(config)
config.limit_time_fraction(0.1)
for i in range(20):
if config.is_time_fraction_limit():
break
df_sample = df.sample(min(3000, len(df)), random_state=i).copy()
transform(df_sample, config_sample)
y = df_sample["target"]
X = df_sample.drop("target", axis=1)
if len(selected_columns) > 0:
X = X.drop(selected_columns, axis=1)
if len(X.columns) > 0:
selected_columns += select_features(X, y, config["mode"])
else:
break
Log.print("Selected columns: {}".format(selected_columns))
drop_number_columns = [c for c in df if c.startswith("number_") and c not in selected_columns]
if len(drop_number_columns) > 0:
config["drop_number_columns"] = drop_number_columns
config["date_columns"] = {}
for c in [c for c in selected_columns if c.startswith("datetime_")]:
d = c.split("_")
date_col = d[0] + "_" + d[1]
date_part = d[2]
if date_col not in config["date_columns"]:
config["date_columns"][date_col] = []
config["date_columns"][date_col].append(date_part)
drop_datetime_columns = [c for c in df if c.startswith("datetime_") and c not in config["date_columns"]]
if len(drop_datetime_columns) > 0:
config["drop_datetime_columns"] = drop_datetime_columns
if "drop_number_columns" in config:
Log.print("Drop number columns: {}".format(config["drop_number_columns"]))
df.drop(config["drop_number_columns"], axis=1, inplace=True)
if "drop_datetime_columns" in config:
Log.print("Drop datetime columns: {}".format(config["drop_datetime_columns"]))
df.drop(config["drop_datetime_columns"], axis=1, inplace=True)
pre="sz"
else:
pre="sh"
symbol=pre+strNum
formatDate=time.strftime("%Y%m%d",time.strptime(date,"%Y%m%d"))
url=detailSource.get("qq2") %(symbol, formatDate)
return url
def handleDetail(code,date,parser , conf):
url=getUrl(num = code,date = date,conf=conf)
fetchData=Fetcher.fetch(url)
parseData=parser.parse(fetchData)
path = Dumper.getPath(code = code , date = date ,dataType = "detail" ,conf = conf)
Dumper.dump(path = path,data = parseData)
return True
if __name__ == '__main__':
import doctest
SYS_HOME=os.path.join(__dir__,"..","..","..")
sys.path.insert(0,SYS_HOME)
from lib.util import Conf,Log
conf=Conf.load(\
os.path.join(SYS_HOME,"conf","stock.yaml"),
os.path.join(SYS_HOME,"conf","downloader.yaml"))
Fetcher.DEBUG=True
logPath=os.path.join(SYS_HOME , conf.get("LOG_PATH",""))
Log.set(logPath = logPath , printLevel=logging.DEBUG)
conf["SYS_HOME"]=SYS_HOME
conf["DEBUG"]=True
doctest.testmod()
"""
"""
init
"""
import os,sys,logging
from lib.stk.element import Stock,Date,Dumper
from lib.util import Log,Conf
__dir__ = os.path.realpath(os.path.dirname(__file__))
APP_HOME=os.path.join(__dir__,"..")
SYS_HOME=os.path.join(APP_HOME,"..")
SYS_LIB_HOME=os.path.join(SYS_HOME,"lib")
sys.path.insert(0,SYS_HOME)
conf=Conf.load(os.path.join(SYS_HOME,"conf","stock.yaml"),os.path.join(SYS_HOME,"conf","downloader.yaml"))
conf["SYS_HOME"] = SYS_HOME
logPath=os.path.join(SYS_HOME , conf.get("LOG_PATH",""))
Log.set(logPath = logPath,printLevel = logging.ERROR)
stock = Stock(conf)
###################### TRAIN
"""
训练 整体 statistics 和 strategic likelihood
用 element/statistics来载入这些数据
"""
TRAIN_DATA_PATH = os.path.join(SYS_HOME,"data","train")
#train all days data and gaussian data
from lib.stk.statistics.Gaussian import Gaussian
subject = [[-0.1,-0.09],[-0.09,-0.08],[-0.08,-0.07],[-0.07,-0.06],[-0.06,-0.05],[-0.05,-0.04],[-0.04,-0.03],[-0.03,-0.02],[-0.02,-0.01],[-0.01,0],[0,0.01],[0.01,0.02],[0.02,0.03],[0.03,0.04],[0.04,0.05],[0.05,0.06],[0.06,0.07],[0.07,0.08],[0.08,0.09],[0.09,0.1]]
# strategic likelihood
from lib.stk.element.Strategic import Strategic
def preview_df(train_csv: str, config: Config, nrows: int = 3000):
num_rows = sum(1 for line in open(train_csv)) - 1
Log.print("Rows in train: {}".format(num_rows))
df = pd.read_csv(train_csv,
encoding="utf-8",
low_memory=False,
nrows=nrows)
mem_per_row = df.memory_usage(deep=True).sum() / nrows
Log.print("Memory per row: {:0.2f} Kb".format(mem_per_row / 1024))
df_size = (num_rows * mem_per_row) / 1024 / 1024
Log.print("Approximate dataset size: {:0.2f} Mb".format(df_size))
config["parse_dates"] = []
config["dtype"] = {
"line_id": int,
}
counters = {
"id": 0,
"number": 0,
"string": 0,
"datetime": 0,
}
for c in df:
if c.startswith("number_"):
counters["number"] += 1
elif c.startswith("string_"):
counters["string"] += 1
config["dtype"][c] = str
elif c.startswith("datetime_"):
counters["datetime"] += 1
config["dtype"][c] = str
config["parse_dates"].append(c)
elif c.startswith("id_"):
counters["id"] += 1
Log.print("Number columns: {}".format(counters["number"]))
Log.print("String columns: {}".format(counters["string"]))
Log.print("Datetime columns: {}".format(counters["datetime"]))
config["counters"] = counters
def time_series_detect(df: pd.DataFrame, config: Config):
sample_size = 10000
model_params = {
"objective": "regression" if config["mode"] == "regression" else "binary",
"metric": "rmse" if config["mode"] == "regression" else "auc",
"learning_rate": 0.01,
"verbosity": -1,
"seed": 1,
"max_depth": -1,
}
if config.is_train():
datetime_columns = [c for c in df if c.startswith("datetime_")]
id_columns = [c for c in df if c.startswith("id_")]
sort_columns = []
for dc in datetime_columns:
sort_columns.append([dc])
for ic in id_columns:
sort_columns.append([ic, dc])
else:
for ic in id_columns:
sort_columns.append([ic])
scores = []
config.limit_time_fraction(0.1)
for sc in sort_columns:
if config.is_time_fraction_limit():
break
Log.silent(True)
df.sort_values(sc, inplace=True)
config_sample = copy.deepcopy(config)
df_sample = df.iloc[-sample_size:].copy() if len(df) > sample_size else df.copy()
df_sample = df_sample[[c for c in df_sample if c.startswith("number_") or c == "target" or c in sc]]
shift_columns(df_sample, group= sc[0] if len(sc) > 1 else None)
transform(df_sample, config_sample)
y = df_sample["target"]
X = df_sample.drop("target", axis=1)
X_train, X_test, y_train, y_test = ts_split(X, y, test_size=0.5)
model_sorted = lgb.train(model_params, lgb.Dataset(X_train, label=y_train), 3000, lgb.Dataset(X_test, label=y_test),
early_stopping_rounds=100, verbose_eval=False)
score_sorted = model_sorted.best_score["valid_0"][model_params["metric"]]
sampled_columns = [c for c in X if "_shift" not in c]
model_sampled = lgb.train(model_params, lgb.Dataset(X_train[sampled_columns], label=y_train), 3000, lgb.Dataset(X_test[sampled_columns], label=y_test),
early_stopping_rounds=100, verbose_eval=False)
score_sampled = model_sampled.best_score["valid_0"][model_params["metric"]]
if config.is_classification():
score_sorted = -score_sorted
score_sampled = -score_sampled
Log.silent(False)
Log.print("Sort: {}. Score sorted: {:0.4f}. Score sampled: {:0.4f}".format(sc, score_sorted, score_sampled))
score_ratio = score_sampled / score_sorted if config.is_regression() else abs(score_sorted / score_sampled)
if score_ratio >= 1.03:
Log.print(score_ratio)
scores.append((score_sorted, sc))
if len(scores) > 0:
scores = sorted(scores, key=lambda x: x[0])
Log.print("Scores: {}".format(scores))
config["sort_values"] = scores[0][1]
df.sort_values(config["sort_values"], inplace=True)
config_sample = copy.deepcopy(config)
df_sample = df.iloc[-sample_size:].copy() if len(df) > sample_size else df.copy()
shift_columns(df_sample, group=config["sort_values"][0] if len(config["sort_values"]) > 1 else None)
transform(df_sample, config_sample)
y = df_sample["target"]
X = df_sample.drop("target", axis=1)
model = lgb.train(model_params, lgb.Dataset(X, label=y), 1000)
fi = pd.Series(model.feature_importance(importance_type="gain"), index=X.columns)
fi = fi[fi > 0].sort_values()
selected_columns = fi[fi >= fi.quantile(0.75)].index.tolist()
selected_shift_columns = [c.replace("_shift", "") for c in selected_columns if "_shift" in c]
if len(selected_shift_columns) > 0:
Log.print("Shift columns: {}".format(selected_shift_columns))
config["shift_columns"] = selected_shift_columns
if "shift_columns" in config:
shift_columns(df, group=config["sort_values"][0] if len(config["sort_values"]) > 1 else None, number_columns=config["shift_columns"])
automl.train("data/check_{}/train.csv".format(alias), mode)
automl.config["time_limit"] = 300
automl.config["start_time"] = time.time()
_, score = automl.predict("data/check_{}/test.csv".format(alias), "predictions/check_{}.csv".format(alias))
return score
if __name__ == '__main__':
scores = {
"dataset": [],
"score": [],
"time": [],
}
for i, mode, train_limit in DATASETS:
alias = "{}_{}".format(i, mode[0])
start_time = time.time()
score = validate_dataset(alias, mode, train_limit)
end_time = time.time()
scores["dataset"].append(alias)
scores["score"].append(score)
scores["time"].append(end_time - start_time)
scores = pd.DataFrame(scores)
scores.to_csv("scores/{}.csv".format(int(time.time())))
Log.print(scores, nesting=False)
logging.error("No %s commands." % cmd_name)
else:
cmd = imp.load_module(cmd_name, fp, pathname, description)
cmd.run(conf = conf)
finally:
if fp:
fp.close()
if __name__=="__main__" :
if sys.argv[1:]:
conf=Conf.load(\
os.path.join(SYS_HOME,"conf","stock.yaml"),
os.path.join(SYS_HOME,"conf","downloader.yaml"))
conf["SYS_HOME"]=SYS_HOME
conf.update(parseArgs(conf))
Log.set(os.path.join(SYS_HOME,conf.get("LOG_PATH")))
action=conf.get("action","run")
dates=conf.get("dates") #如果指定多个日期，则按顺序启动实例一个一个运行
stockCache = {} #@todo add stockCache
if not dates or len(dates)==0:
conf['date']=Date.getDate()
execute(cmd_name = action,conf=conf)
elif len(dates)>=1:
for sDate in dates:
conf["date"]=sDate
if stockCache:
conf['stock']=stockCache
execute(cmd_name = action,conf=conf)
else:
print __doc__
m = item
else:
m = (item - expection)/(deviation *(2 **0.5))
#res = 0.5 * (1 + norm.cdf(m))
res = 0.5 * (1 + special.erf(m))
if preValue !=None :
ret = res - preValue
else:
preValue = res
ret = res
return ret
if __name__ == '__main__':
import doctest
SYS_HOME=os.path.join(LIB_HOME,"..","..")
sys.path.insert(0,SYS_HOME)
from lib.util import Log,Conf
conf=Conf.load(\
os.path.join(SYS_HOME,"conf","stock.yaml"),
os.path.join(SYS_HOME,"conf","downloader.yaml")
)
conf["SYS_HOME"] = SYS_HOME
logPath=os.path.join(SYS_HOME , conf.get("LOG_PATH",""))
Log.set(logPath = logPath)
gaussian = Gaussian()
stock = Stock(conf)
stock.date = '20111024'
doctest.testmod()
def validate(preds: pd.DataFrame, target_csv: str, mode: str) -> np.float64:
df = pd.merge(preds, pd.read_csv(target_csv), on="line_id", left_index=True)
score = roc_auc_score(df.target.values, df.prediction.values) if mode == "classification" else \
np.sqrt(mean_squared_error(df.target.values, df.prediction.values))
Log.print("Score: {:0.4f}".format(score))
return score
