Cannot call causalml.inference.tree or causalml.dataset

[Cici-J-github]

Describe the bug
A clear and concise description of what the bug is.
Hey I followed exactly steps listed here https://github.com/uber/causalml but I get bugs when I run this line from causalml.dataset import synthetic_data but I got an error saying ValueError: sklearn.tree._tree.TreeBuilder size changed, may indicate binary incompatibility. Expected 80 from C header, got 72 from PyObject
To Reproduce
Steps to reproduce the behavior:
$ git clone https://github.com/uber/causalml.git
$ cd causalml
$ pip install -r requirements.txt
$ pip install causalml
from causalml.dataset import synthetic_data
from causalml.inference.tree import UpliftTreeClassifier, UpliftRandomForestClassifier

Expected behavior
A clear and concise description of what you expected to happen.

Screenshots
If applicable, add screenshots to help explain your problem.

Environment (please complete the following information):

• OS: [e.g. macOS]
• Python Version: [3.7.3]
• sklearn:1.0.2
• causalml:0.13.0

Additional context
Pls help fix it

[jakirhasantalukder]

same problem

[guilhermeresende]

I also have this problem

[xhulianoThe1]

What numpy version are you running? A quick solve could be upgrading your numpy version.

[jakirhasantalukder]

Hi everyone, My code is working from google colab. Please try this code-

! git clone https://github.com/uber/causalml.git
! cd causalml
! pip install -r /content/causalml/requirements-test.txt
! pip install causalml[tf]
! pip install -U numpy==1.23.5

[StarMaye]

same problem

[jakirhasantalukder]

Initially run the following code:

!pip install Causalml
!pip install numpy==1.23.5

!git clone https://github.com/uber/causalml.git
!cd causalml
!pip install -r /content/causalml/requirements.txt
!python setup.py build_ext --inplace
!pip /content/causalml/setup.py install
!python setup.py install

! git clone https://github.com/uber/causalml.git
! cd causalml
! pip install -r /content/causalml/requirements-test.txt
! pip install causalml[tf]
! pip install -U numpy==1.23.5

!pip install numpy==1.23.4

!pip install -U scikit-learn==1.0.2

!pip uninstall scikit-learn
!pip install scikit-learn==1.0.2

when show- Proceed (Y/n)? Put Y and then enter; Then run-

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
import seaborn as sns
import torch

from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from xgboost import XGBRegressor
from lightgbm import LGBMRegressor
from sklearn.metrics import mean_absolute_error
from sklearn.metrics import mean_squared_error as mse
from scipy.stats import entropy
import warnings
import logging

from causalml.inference.meta import BaseXRegressor, BaseRRegressor, BaseSRegressor, BaseTRegressor
from causalml.inference.nn import CEVAE
from causalml.propensity import ElasticNetPropensityModel
from causalml.metrics import *
from causalml.dataset import simulate_hidden_confounder

%matplotlib inline

warnings.filterwarnings('ignore')
logger = logging.getLogger('causalml')
logger.setLevel(logging.DEBUG)

plt.style.use('fivethirtyeight')
sns.set_palette('Paired')
plt.rcParams['figure.figsize'] = (12,8)

When it is not running, go to "Runtime" and click on "Restart and run all"

It will definitely work in google colab, but do not forget # when show- Proceed (Y/n)? Put Y and then enter

[MingyueHe]

hi @jakirhasantalukder
I also encounter this issue. I successfully install causalml, but I cannot call causalml.inference.tree.

numpy version: 1.23.5
scikit-learn: 1.0.2
I receive the following errors when calling the class in causalml.inference.tree:
from causalml.inference.tree import CausalTreeRegressor
Traceback (most recent call last):

Input In [1] in <cell line: 1>
from causalml.inference.tree import CausalTreeRegressor

File ~\Anaconda3\lib\site-packages\causalml\inference\tree_init_.py:1 in
from .causal.causaltree import CausalTreeRegressor

File ~\Anaconda3\lib\site-packages\causalml\inference\tree\causal\causaltree.py:14 in
from causalml.inference.meta.utils import check_treatment_vector

File ~\Anaconda3\lib\site-packages\causalml\inference\meta_init_.py:1 in
from .slearner import LRSRegressor, BaseSLearner, BaseSRegressor, BaseSClassifier

File ~\Anaconda3\lib\site-packages\causalml\inference\meta\slearner.py:9 in
from causalml.inference.meta.base import BaseLearner

File ~\Anaconda3\lib\site-packages\causalml\inference\meta\base.py:6 in
from causalml.inference.meta.explainer import Explainer

File ~\Anaconda3\lib\site-packages\causalml\inference\meta\explainer.py:2 in
import shap

File ~\Anaconda3\lib\site-packages\shap_init_.py:5 in
from ._explanation import Explanation, Cohorts

File ~\Anaconda3\lib\site-packages\shap_explanation.py:13 in
from .utils._exceptions import DimensionError

File ~\Anaconda3\lib\site-packages\shap\utils_init_.py:1 in
from ._clustering import (

File ~\Anaconda3\lib\site-packages\shap\utils_clustering.py:7 in
from numba import njit

File ~\Anaconda3\lib\site-packages\numba_init_.py:200 in
_ensure_critical_deps()

File ~\Anaconda3\lib\site-packages\numba_init_.py:140 in _ensure_critical_deps
raise ImportError("Numba needs NumPy 1.21 or less")

ImportError: Numba needs NumPy 1.21 or less

If I install numpy==1.20.1, I receive the following errors:
from causalml.inference.tree import CausalTreeRegressor
Traceback (most recent call last):

Input In [1] in <cell line: 1>
from causalml.inference.tree import CausalTreeRegressor

File ~\Anaconda3\lib\site-packages\causalml\inference\tree_init_.py:1 in
from .causal.causaltree import CausalTreeRegressor

File ~\Anaconda3\lib\site-packages\causalml\inference\tree\causal\causaltree.py:15 in
from ._tree import BaseCausalDecisionTree

File ~\Anaconda3\lib\site-packages\causalml\inference\tree\causal_tree.py:16 in
from ._builder import DepthFirstCausalTreeBuilder, BestFirstCausalTreeBuilder

File causalml\inference\tree\causal_builder.pyx:1 in init causalml.inference.tree.causal._builder

ValueError: numpy.ndarray size changed, may indicate binary incompatibility. Expected 96 from C header, got 88 from PyObject

Could you please help me with it?

[kihaddadi]

Hi, I am a databricks user and attempted to install causalml library using
%pip install causalml numpy==1.20.3
which generated the follwoing error when I attempted to load casualml.dataset
from causalml.dataset import synthetic_data
Error:
ValueError: numpy.ndarray size changed, may indicate binary incompatibility. Expected 96 from C header, got 88 from PyObject

I also attempted to install a newer version of numpy:
%pip install causalml numpy==1.23.5
which generated the following error:
ImportError: cannot import name '_centered' from 'scipy.signal.signaltools' (/local_disk0/.ephemeral_nfs/envs/pythonEnv-a32dc5df-a476-437e-ad17-39bfbcff6a58/lib/python3.8/site-packages/scipy/signal/signaltools.py
Can you please help me?

[ImanEmtiazi728]

i cannot run the S-learner in my code. I wrote the code below for my dataset, which is attached to this comment.

import pandas as pd

Load your dataset

file_path = r'/content/prices (2).csv'
your_data = pd.read_csv(file_path)

Assign columns to X and y

y = your_data['HolidayFlag']
X = your_data['SMPEP2']
prices (2).csv

Ready-to-use S-Learner using LinearRegression

learner_s = LRSRegressor()
ate_s = learner_s.estimate_ate(X=X, treatment=treatment, y=y)
print(ate_s)
print('ATE estimate: {:.03f}'.format(ate_s[0][0]))
print('ATE lower bound: {:.03f}'.format(ate_s[1][0]))
print('ATE upper bound: {:.03f}'.format(ate_s[2][0]))

After calling estimate_ate, add pretrain=True flag to skip training

This flag is applicable for other meta learner

ate_s = learner_s.estimate_ate(X=X, treatment=treatment, y=y, pretrain=True)
print(ate_s)
print('ATE estimate: {:.03f}'.format(ate_s[0][0]))
print('ATE lower bound: {:.03f}'.format(ate_s[1][0]))
print('ATE upper bound: {:.03f}'.format(ate_s[2][0]))

the below error recived;

IndexError Traceback (most recent call last)
in <cell line: 3>()
1 # Ready-to-use S-Learner using LinearRegression
2 learner_s = LRSRegressor()
----> 3 ate_s = learner_s.estimate_ate(X=X, treatment=treatment, y=y)
4 print(ate_s)
5 print('ATE estimate: {:.03f}'.format(ate_s[0][0]))

1 frames
/usr/local/lib/python3.10/dist-packages/causalml/inference/meta/slearner.py in fit(self, X, treatment, y, p)
84 mask = (treatment == group) | (treatment == self.control_name)
85 treatment_filt = treatment[mask]
---> 86 X_filt = X[mask]
87 y_filt = y[mask]
88

IndexError: boolean index did not match indexed array along dimension 0; dimension is 10000 but corresponding boolean dimension is 9885

could anybody help me with that?

[ImanEmtiazi728]

I'm using the code in https://github.com/uber/causalml/blob/master/docs/examples/meta_learners_with_synthetic_data.ipynb.
but when i wanted to run the slearner for the datset
prices (2).csv
.in my dataset, HolidayFlag' dataset is y and SMPEP2 is X.

I recieved the below error for the above code

Could you please help me with that?