sklearn2vantage 0.1.9

依赖项

sklearn2vantage 需要：

• Python

• 数字货币

• 熊猫

• SQL炼金术

• scikit-学习

• 帕拉米科

• scp

• 兆数据

• sqlalchemy-teradata

• teradatasql

• teradatasql炼金术

支持的型号

支持以下型号。

还支持 statsmodels 中的一些模型。

用户安装

pip install sklearn2vantage

或者

conda install sklearn2vantage -c temporary-recipes

示例：对流模型

import sklearn2vantage as s2v
import pandas as pd
from sqlalchemy import create_engine
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier

engine = create_engine("teradata://dbc:dbc@173.168.56.128:1025/tdwork")

df = pd.read_sql_query("select * from some_data sample 50000", engine)
X = df.drop("target", axis=1)
y = df.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25)

rf_clf = RandomForestClassifier()
rf_clf.fit(X_train, y_train)

rf_clf_table = \
  s2v.make_model_table_forest(rf_clf, X_train.columns,
                              ['setosa', 'versicolor', 'virginica'])

s2v.load_model_forest(rf_clf_table, engine, "rf_clf_table")
pd.read_sql_query("""
  select * from DecisionForestPredict (
    on iris partition by any
    on rf_clf_table as ModelTable DIMENSION
    USING
    NumerixInputs ('sepal_length', 'sepal_width',
                  'petal_length', 'petal_width')
    IdColumn ('id')
    Accumulate ('species')
    Detailed ('false')
) as dt""", engine)

如需进一步使用，请参阅HowToUse.ipynb。

示例：数据加载

import pandas as pd
import sklearn2vantage as s2v
from sqlalchemy import create_engine
engine = create_engine("teradata://dbc:dbc@173.168.56.128:1025/tdwork")
df_titanic = pd.read_csv("titanic/train.csv").set_index("PassengerId")
s2v.tdload_df(df_titanic, engine, tablename="titanic_train",
              ifExists="replace", ssh_ip="173.168.56.128",
              ssh_username="root", ssh_password="root")

如需进一步使用，请参阅HowToUseDataloader.ipynb。