Created
June 5, 2013 21:06
-
-
Save glamp/5717321 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from sklearn.datasets import load_iris | |
| from sklearn.ensemble import RandomForestClassifier | |
| import pandas as pd | |
| import numpy as np | |
| iris = load_iris() | |
| df = pd.DataFrame(iris.data, columns=iris.feature_names) | |
| df['is_train'] = np.random.uniform(0, 1, len(df)) <= .75 | |
| df['species'] = pd.Factor(iris.target, iris.target_names) | |
| df.head() | |
| train, test = df[df['is_train']==True], df[df['is_train']==False] | |
| features = df.columns[:4] | |
| clf = RandomForestClassifier(n_jobs=2) | |
| y, _ = pd.factorize(train['species']) | |
| clf.fit(train[features], y) | |
| preds = iris.target_names[clf.predict(test[features])] | |
| pd.crosstab(test['species'], preds, rownames=['actual'], colnames=['preds']) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
agreed ^ Pandas.Factor doesn't work. As of 2/12/2016 it's
df['species'] = pd.Categorical.from_codes(iris.target, iris.target_names)