I'm new to sklearn and having trouble formatting the data to predict and evaluate a confusion matrix. I'm using this Random Forest tutorial.

Here is my code

 from sklearn.ensemble import RandomForestClassifier
 import numpy as np
 import pandas as pd
 dataframe = pd.read_csv('output.txt', sep='\t')
 df = pd.DataFrame(dataframe)
 df['is_train'] = np.random.uniform(0, 1, len(df)) <= .75

 train, test = df[df['is_train']==True], df[df['is_train']==False]
 features = df.columns[1:5]
 clf = RandomForestClassifier(n_jobs=2)
 y, _ = pd.factorize(train['event_count'])
 clf.fit(train[features], y)

It's this line for my predictions which is giving me the error:

 preds = df[:6][clf.predict(test[features])]
 IndexError: only integers, slices (`:`), ellipsis (`...`), numpy.newaxis (`None`) and integer or boolean arrays are valid indices

It is not possible to write numpy style slices in dataframe, like :

observations = data[:6]

Try DataFrame.ix


Cf panda indexing : Panda indexing

  • $\begingroup$ my issue was my 'test' variable did not get exectuted the first time around. so now that works. $\endgroup$ – Bachzen Dec 2 '16 at 19:00

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.