Crowdflower: Data for Everyone (public dataset)
Crowdflower
pip install mit-d3m
from mit_d3m import load_dataset
dataset = load_dataset('LL1_sentiment_self_drive')
X = dataset.X
y = dataset.y
context = dataset.context
0.5933334714143366
mlprimitives.preprocessing.ClassEncoder
featuretools.dfs
sklearn.preprocessing.Imputer
sklearn.preprocessing.StandardScaler
xgboost.XGBClassifier
mlprimitives.preprocessing.ClassDecoder
mlprimitives.preprocessing.ClassEncoder#1
featuretools.dfs#1
"encode": true
"max_depth": 1
"remove_low_information": true
sklearn.preprocessing.Imputer#1
"missing_values": NaN
"axis": 0
"copy": true
"strategy": most_frequent
sklearn.preprocessing.StandardScaler#1
"with_mean": false
"with_std": true
xgboost.XGBClassifier#1
"n_jobs": -1
"n_estimators": 311
"max_depth": 3
"learning_rate": 0.05464565610798644
"gamma": 0.8326572646287191
"min_child_weight": 7
mlprimitives.preprocessing.ClassDecoder#1
| ColIndex | ColName | ColType | Role |
|---|