#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Mon Oct  5 09:50:24 2020

@author: tanya
"""

from sklearn.ensemble import RandomForestClassifier
from sklearn.feature_selection import SelectPercentile
from sklearn.linear_model import LogisticRegression
from sklearn.decomposition import PCA
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from hyperopt import hp
import numpy as np


space = hp.choice("pipelines", [

        {"name": "std_scaler_kbest_rf",
         "pipeline": Pipeline([
                 ("std_scaler", StandardScaler()),
                 ("kbest", SelectPercentile()),
                 ("rf", RandomForestClassifier())]),
         "params": {"kbest__percentile":
                    hp.choice('kbest__percentile', range(1, 3)),
                    "rf__n_estimators":
                    50 + hp.randint('rf__n_estimators', 50)}},

        {"name": "std_scaler_pca_lr",
         "pipeline": Pipeline([
                 ("std_scaler", StandardScaler()),
                 ("pca", PCA()),
                 ("lr", LogisticRegression())]),
         "params": {"lr__C":
                    hp.loguniform("lr__C", np.log(0.01), np.log(0.1)),
                    "pca__n_components":
                    1 + hp.randint("pca__n_components", 4)}}
        ])