from bartpy.sklearnmodel import SklearnModel
from bartpy.featureselection import SelectNullDistributionThreshold, SelectSplitProportionThreshold
from bartpy.diagnostics.features import *

ModuleNotFoundError Traceback (most recent call last) in ----> 1 from bartpy.sklearnmodel import SklearnModel 2 from bartpy.featureselection import SelectNullDistributionThreshold, SelectSplitProportionThreshold 3 from bartpy.diagnostics.features import *

~/miniconda3/envs/viz/lib/python3.7/site-packages/bartpy/sklearnmodel.py in 9 from bartpy.data import Data 10 from bartpy.model import Model ---> 11 from bartpy.samplers.leafnode import LeafNodeSampler 12 from bartpy.samplers.modelsampler import ModelSampler, Chain 13 from bartpy.samplers.schedule import SampleSchedule

ModuleNotFoundError: No module named 'bartpy.samplers'

from bartpy.samplers import *

ModuleNotFoundError Traceback (most recent call last) in ----> 1 from bartpy.samplers import *

ModuleNotFoundError: No module named 'bartpy.samplers'

Open to "import SklearnModel"

import bartpy
from bartpy.sklearnmodel import SklearnModel

ModuleNotFoundError                       Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_1232/2717476998.py in <module>
----> 1 from bartpy.sklearnmodel import SklearnModel

~\Anaconda3\envs\env\lib\site-packages\bartpy\sklearnmodel.py in <module>
      9 from bartpy.data import Data
     10 from bartpy.model import Model
---> 11 from bartpy.samplers.leafnode import LeafNodeSampler
     12 from bartpy.samplers.modelsampler import ModelSampler, Chain
     13 from bartpy.samplers.schedule import SampleSchedule

ModuleNotFoundError: No module named 'bartpy.samplers'

Hi,

I just installed the bartpy locally in my machine and I am trying to run the example code ols.py. I am getting the following error, please advise.

0%| | 0/50 [00:00<?, ?it/s]2020-01-27 13:38:26.026932 Starting burn

Traceback (most recent call last):

File "", line 1, in runfile('/Users/anita/Bayesian/bartpy-master/examples/ols.py', wdir='/Users/anita/Bayesian/bartpy-master/examples')

File "/Users/anita/opt/anaconda3/lib/python3.7/site-packages/spyder_kernels/customize/spydercustomize.py", line 827, in runfile execfile(filename, namespace)

File "/Users/anita/opt/anaconda3/lib/python3.7/site-packages/spyder_kernels/customize/spydercustomize.py", line 110, in execfile exec(compile(f.read(), filename, 'exec'), namespace)

File "/Users/anita/Bayesian/bartpy-master/examples/ols.py", line 26, in model, x, y = run(0.95, 2., 20, 5)

File "/Users/anita/Bayesian/bartpy-master/examples/ols.py", line 15, in run model.fit(X, y)

File "/Users/anita/opt/anaconda3/lib/python3.7/site-packages/bartpy-0.0.2-py3.7.egg/bartpy/sklearnmodel.py", line 134, in fit self.extract = Parallel(n_jobs=self.n_jobs)(self.f_delayed_chains(X, y))

File "/Users/anita/opt/anaconda3/lib/python3.7/site-packages/joblib/parallel.py", line 921, in call if self.dispatch_one_batch(iterator):

File "/Users/anita/opt/anaconda3/lib/python3.7/site-packages/joblib/parallel.py", line 759, in dispatch_one_batch self._dispatch(tasks)

File "/Users/anita/opt/anaconda3/lib/python3.7/site-packages/joblib/parallel.py", line 716, in _dispatch job = self._backend.apply_async(batch, callback=cb)

File "/Users/anita/opt/anaconda3/lib/python3.7/site-packages/joblib/_parallel_backends.py", line 182, in apply_async result = ImmediateResult(func)

File "/Users/anita/opt/anaconda3/lib/python3.7/site-packages/joblib/_parallel_backends.py", line 549, in init self.results = batch()

File "/Users/anita/opt/anaconda3/lib/python3.7/site-packages/joblib/parallel.py", line 225, in call for func, args, kwargs in self.items]

File "/Users/anita/opt/anaconda3/lib/python3.7/site-packages/joblib/parallel.py", line 225, in for func, args, kwargs in self.items]

File "/Users/anita/opt/anaconda3/lib/python3.7/site-packages/bartpy-0.0.2-py3.7.egg/bartpy/sklearnmodel.py", line 31, in run_chain model.store_acceptance_trace)

File "/Users/anita/opt/anaconda3/lib/python3.7/site-packages/bartpy-0.0.2-py3.7.egg/bartpy/samplers/modelsampler.py", line 43, in samples self.step(model, trace_logger)

File "/Users/anita/opt/anaconda3/lib/python3.7/site-packages/bartpy-0.0.2-py3.7.egg/bartpy/samplers/modelsampler.py", line 26, in step result = step()

File "/Users/anita/opt/anaconda3/lib/python3.7/site-packages/bartpy-0.0.2-py3.7.egg/bartpy/samplers/schedule.py", line 48, in yield "Tree", lambda: self.tree_sampler.step(model, tree)

File "/Users/anita/opt/anaconda3/lib/python3.7/site-packages/bartpy-0.0.2-py3.7.egg/bartpy/samplers/unconstrainedtree/treemutation.py", line 47, in step mutation = self.sample(model, tree)

File "/Users/anita/opt/anaconda3/lib/python3.7/site-packages/bartpy-0.0.2-py3.7.egg/bartpy/samplers/unconstrainedtree/treemutation.py", line 40, in sample ratio = self.likihood_ratio.log_probability_ratio(model, tree, proposal)

File "/Users/anita/opt/anaconda3/lib/python3.7/site-packages/bartpy-0.0.2-py3.7.egg/bartpy/samplers/treemutation.py", line 80, in log_probability_ratio return self.log_transition_ratio(tree, mutation) + self.log_likihood_ratio(model, tree, mutation) + self.log_tree_ratio(model, tree, mutation)

File "/Users/anita/opt/anaconda3/lib/python3.7/site-packages/bartpy-0.0.2-py3.7.egg/bartpy/samplers/unconstrainedtree/likihoodratio.py", line 69, in log_likihood_ratio mutation: GrowMutation = mutation

UnboundLocalError: local variable 'mutation' referenced before assignment

This seems like a pretty easy win given how parallelizable the different chains are.

The current solution is to follow sklearn and pymc in using joblib to handle the parallelization. A nice feature of this is that it looks relatively easy to make this solution scale into a full dask cluster approach.

To assess convergence to the true distribution, it is useful to run several chains from different start points. At the moment, this requires running the model multiple times in parallel.

There are two related parts of this issue:

1. conceptually support multiple chains in the API
2. use multiprocessing of the like to parallelize

1. The example "Comparison of model with sine waves" gives an error because of the log_likihood_ratio().

2. catboos' may be not appropreate for requirements.txt. It is upto you.

A number of architectural changes to make things run much faster. Primary changes:

• much more aggressive caching
• switching from masked arrays to more direct numpy logic

The main change in this PR is to reshuffle how Data works. Rather than every split causing a deepcopy of the X and y matrices, it now only creates new masks onto a single instance of X and y. This makes the process much faster and lighter on memory

There's also an embarrassing splodge of other changes at the same time :(

Rather than holding state in the samplers, it's nicer to have them be stateless and pure. This also allows much easier injection of different sampling methods

Hello, It is quite interesting to have an implementation of BART in python. However, when I tried this implementation with its alternative in R "bartMachine", the alternative was giving more promising results. Can you tell, if you had the time to explore it of course, the difference between your implementation and the one of bartMachine?

Thank you in advance :)

Are there plans to add dichotomous outcomes and random intercepts to this model? Another question is how one would incorporate the random intercepts to conditional means for prediction of the dichotomous outcome? Thanks!

https://github.com/vdorie/dbarts/blob/4ed4eafc772e95d788d5a135d9f4e4728b9516ec/R/rbart.R#L5

Hi,

Thank you for bart-py!

My BART model is predicting NaN for some cases. Does anyone know why this happens? or how I can prevent this?

My data has missing data but to my knowledge, BART can handle this. My data are finite.

Thank you!

Code: (Sorry for the lengthy data generation)

import pandas as pd
import numpy as np
import random
import bartpy
from bartpy.sklearnmodel import SklearnModel
import sklearn
from sklearn.model_selection import train_test_split
from sklearn.model_selection import KFold

# simulate df with 46 features and 9000 rows
# create binary vars and make a df
label=np.random.randint(2, size=9000)
df = pd.DataFrame({'label':label})
df['a']=np.random.randint(2, size=9000)

# create integers
df['b'] = np.random.randint(low=50, high=96, size=9000)
df['b'] = np.random.randint(low=4, high=97, size=9000)
df['c'] = np.random.randint(low=0, high=1759.22, size=9000)
df['d'] = np.random.randint(low=0, high=5702.2, size=9000)
df['e'] = np.random.randint(low=0, high=7172.31, size=9000)

# create numerics
df['f'] = np.random.uniform(0, 908.56, 9000)
df['f'] = np.random.uniform(0,908.56, 9000)
df['g'] = np.random.uniform(0,2508.78, 9000)
df['h'] = np.random.uniform(0,3757.56, 9000)
df['i'] = np.random.uniform(0,560.18, 9000)
df['j'] = np.random.uniform(0,1362.71, 9000)
df['k'] = np.random.uniform(0,2578.26, 9000)
df['l'] = np.random.uniform(175.07,997, 9000)
df['m'] = np.random.uniform(992.39,3972.81, 9000)
df['n'] = np.random.uniform(1787.24,5823.21, 9000)
df['o'] = np.random.uniform(-56,53, 9000)
df['p'] = np.random.uniform(-47,46, 9000)
df['q'] = np.random.uniform(-1089.03,1546.87, 9000)
df['r'] = np.random.uniform(-1599.14,898.79, 9000)
df['s'] = np.random.uniform(-2871.02,5329, 9000)
df['t'] = np.random.uniform(-4231.44,2481.55, 9000)
df['u'] = np.random.uniform(-3435.9,5824.22, 9000)
df['v'] = np.random.uniform(-5086.6,4548.43, 9000)
df['w'] = np.random.uniform(-406.57,907.91, 9000)
df['x'] = np.random.uniform(-834.82,840.27, 9000)
df['y'] = np.random.uniform(-549.2,2506.29, 9000)
df['z'] = np.random.uniform(-1547.2,2434.18, 9000)
df['aa'] = np.random.uniform(-426.6,3636.17, 9000)
df['bb'] = np.random.uniform(-2819.8,3390, 9000)
df['cc'] = np.random.uniform(-266.75,527.81, 9000)
df['dd'] = np.random.uniform(-778.64,527.81, 9000)
df['ee'] = np.random.uniform(-476.09,1358.32, 9000)
df['ff'] = np.random.uniform(-1890.91,919.3, 9000)
df['gg'] = np.random.uniform(-1633.23,2577.01, 9000)
df['hh'] = np.random.uniform(-2427.93,2078.78, 9000)
df['ii'] = np.random.uniform(-339.67,518.32, 9000)
df['jj'] = np.random.uniform(-528.07,412, 9000)
df['kk'] = np.random.uniform(-1460.23,1610.58, 9000)
df['ll'] = np.random.uniform(-1984.08,1127.82, 9000)
df['mm'] = np.random.uniform(-2153.38,2402.24, 9000)
df['nn'] = np.random.uniform(-2311.27,1809.37, 9000)
df['oo'] = np.random.uniform(16,92, 9000)
df['pp'] = np.random.uniform(4,24, 9000)
df['qq'] = np.random.uniform(4,80, 9000)
df['rr'] = np.random.uniform(0,1, 9000)

# add missings to floats
# select only numeric columns to apply the missingness to
cols_list = df.select_dtypes('float64').columns.tolist()
        
# randomly remove cases from the dataframe
for col in df[cols_list]:
    df.loc[df.sample(frac=0.02).index, col] = np.nan

# # 80/20 train test split
X_train, X_test, y_train, y_test = train_test_split(df.drop(['label'],axis=1), df['label'], train_size=0.7, random_state = 99)

# Modelling
model = SklearnModel(n_jobs = 30) 
model.fit(X_train, y_train) 

# Predictions
y_predictions = model.predict(X_test)
np.isnan(y_predictions).sum() 

Since the code is written in pure python, a simple step at the end to improve performance is to compile it all using Cython. It's relatively simple to set up and the speedups are great for looped code, so it might be worth looking into.