Added tests for notebooks and fixed confidence interval bug for econml (#204)
* fixed econml bug for CI intervals, * removed input prompt from notebooks to enable automatic testing * added tests for notebooks * added nbformat, jupyter as req for github actions * adding jupyter as dependency for workflow runs * modified readme to be compliant with twine requirements
This commit is contained in:
Amit Sharma
GitHub
Родитель
04a640628e
Коммит
b3234704e8
|
|
@ -28,7 +28,7 @@ jobs:
|
|||
python -m pip install --upgrade pip
|
||||
pip install flake8 pytest twine
|
||||
if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
|
||||
pip install econml causalml
|
||||
pip install econml causalml nbformat jupyter
|
||||
- name: Lint with flake8
|
||||
run: |
|
||||
# stop the build if there are Python syntax errors or undefined names
|
||||
|
|
|
|||
|
|
@ -482,7 +482,7 @@ Bibtex::
|
|||
|
||||
Roadmap
|
||||
=======
|
||||
The `projects <https://github.com/microsoft/dowhy/projects>`_ page lists the next steps for DoWhy. If you would like to contribute, have a look at the current projects. If you have a specific request for DoWhy, please raise an issue `here <https://github.com/microsoft/dowhy/issues>`_.
|
||||
The `projects <https://github.com/microsoft/dowhy/projects>`_ page lists the next steps for DoWhy. If you would like to contribute, have a look at the current projects. If you have a specific request for DoWhy, please `raise an issue <https://github.com/microsoft/dowhy/issues>`_.
|
||||
|
||||
Contributing
|
||||
============
|
||||
|
|
|
|||
|
|
@ -104,12 +104,12 @@
|
|||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"image/png": "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\n",
|
||||
"image/png": "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\n",
|
||||
"text/latex": [
|
||||
"$\\displaystyle 1.625771192059154$"
|
||||
"$\\displaystyle 1.6199979987251836$"
|
||||
],
|
||||
"text/plain": [
|
||||
"1.625771192059154"
|
||||
"1.6199979987251836"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
|
|
@ -172,27 +172,15 @@
|
|||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"INFO:dowhy.causal_identifier:Common causes of treatment and outcome:['Z', 'U']\n",
|
||||
"WARNING:dowhy.causal_identifier:If this is observed data (not from a randomized experiment), there might always be missing confounders. Causal effect cannot be identified perfectly.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"WARN: Do you want to continue by ignoring any unobserved confounders? (use proceed_when_unidentifiable=True to disable this prompt) [y/n] y\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"INFO:dowhy.causal_identifier:Instrumental variables for treatment and outcome:[]\n"
|
||||
"WARNING:dowhy.causal_identifier:If this is observed data (not from a randomized experiment), there might always be missing confounders. Causal effect cannot be identified perfectly.\n",
|
||||
"INFO:dowhy.causal_identifier:Continuing by ignoring these unobserved confounders because proceed_when_unidentifiable flag is True.\n",
|
||||
"INFO:dowhy.causal_identifier:Instrumental variables for treatment and outcome:[]\n",
|
||||
"INFO:dowhy.causal_identifier:Frontdoor variables for treatment and outcome:[]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"identification = model.identify_effect()"
|
||||
"identification = model.identify_effect(proceed_when_unidentifiable=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -211,7 +199,6 @@
|
|||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"INFO:dowhy.causal_identifier:Common causes of treatment and outcome:['Z', 'U']\n",
|
||||
"WARNING:dowhy.causal_identifier:If this is observed data (not from a randomized experiment), there might always be missing confounders. Causal effect cannot be identified perfectly.\n"
|
||||
]
|
||||
},
|
||||
|
|
@ -227,6 +214,7 @@
|
|||
"output_type": "stream",
|
||||
"text": [
|
||||
"INFO:dowhy.causal_identifier:Instrumental variables for treatment and outcome:[]\n",
|
||||
"INFO:dowhy.causal_identifier:Frontdoor variables for treatment and outcome:[]\n",
|
||||
"INFO:dowhy.do_sampler:Using WeightingSampler for do sampling.\n",
|
||||
"INFO:dowhy.do_sampler:Caution: do samplers assume iid data.\n"
|
||||
]
|
||||
|
|
@ -238,7 +226,8 @@
|
|||
"sampler = WeightingSampler(df,\n",
|
||||
" causal_model=model,\n",
|
||||
" keep_original_treatment=True,\n",
|
||||
" variable_types={'D': 'b', 'Z': 'c', 'Y': 'c'})\n",
|
||||
" variable_types={'D': 'b', 'Z': 'c', 'Y': 'c'}\n",
|
||||
" )\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
|
|
@ -267,12 +256,12 @@
|
|||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"image/png": "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\n",
|
||||
"image/png": "iVBORw0KGgoAAAANSUhEUgAAANIAAAASCAYAAAAucYD2AAAHz0lEQVR4nO3ae7BXVRUH8A9IoamBYyHTk0dSZDapRVlCYEkJltK7RntMSI049EJpaBRwpgErGaSawswybLQkKhvIFzICPWxKqMgMFBCBNBEhDDBF+2PtMxzOPefe3zm/e//qfmfu7N/dZ+2z1ll7r70ee/eZPXu2XvSiF+2hb0nfy3AdduApbMECHFfz3X1wIe7Bk/gP/ojPVvCFibgd27Afm3AzTq+gvxIr8HCi34W1mIXjS+iPx2T8HA+kMXuwBp8ukeuTeK6Lv4MVsuVxfo5+cjfIlUddndWhb0cueEca+4hYSztwGyaU0G5RreNHuolHEd02L/0KA4fjtxiEX+J+jMLn8G68DY+3ICDcgI/hX7gR+3AWvoO34uMF+itxaXr/L7ATr8K5eH+iv6Ew5gu4F3ckPkfjLZiNKen3wzn6Dyb+/8RKbMUJeB+uxdmJ5rlEvw5zKr5vNM7ErzvRAbwc3xKbyTEVNHXlylBXZ3Xpm8oFX8MlwmBvSbxejNMwFstLxuwRm3YRT5b0NeWRoVvnpU8htLsN4zEN38z1zxeLdpHwKF1hEpZiszDEnan/+fgZzhETtzT1D8Z2PIbXC6PIMA53pXcNK/A5EgdK+H8VM4USLsr1nymMbRmezfUPxh+Ecj+QZOwKvxOGeq6YxDL0EUY+VHzrdOGlry3QNZGrrs6a6Lipvi7ENbhebGj/LTx/Hp4u9G1J7RCtoQmPDN0+L3nXPFwY0RZ8u/DCWSI0uyC9uCtMSu1VDhkR8bGXpd8X5/pfKdzkPQ6fYGIn2Ct2miLKjAh+mtoTC/134VcOVwoRFnw3/R5b8c48ThZGtF0ouQrTxGR8SuivCk3kqquzJjpuIld/sZFtVb7AqV7graJdHt0+L3lDGpfa20sG7sVv8AKxgLrC4NRuKnmW9Y0WHgo2CmWMwosK9GNwLO5sgW+G96T2LzXGZIp/pgXaKan9vuocaSTm4WqsqiFHq3LV1Vl367hKrrOEQS4V62giZoj0oCpvy9Bf5C0zE/04HFFC1w6PHpmXfI706tRuqBi4UXisESLB7wyZFxpa8iwLHfql3/eLIsEMEULeJ+L3x4WXfK9ww5/phN90EecOwBtxhjCieV3ImaGfQznbrV3QHiUm+6COoUD+fYvFjjmzRRnqylVXZ+3quFW53pTaA6Lw87rC81UiHHqs5L2Dhd7y2Cw8x93dwKPH5iVvSANSu6dicNY/sAVGy/BRfBE3iUkk4tZ88p6vBC4QYeV1Il7N8AB+qGM4ksd0kQRmuFVU3MomqwzzxGQsF3liZ/iQ0MEyhxcy8rgcpwiD3t+iDE3kWqCezurSN5FrUGovEQY7WhRthuIbYjO+WceQ8AdYjb+JCGiYCP+niILO6fhzmzx6bF66Kl82xU2JwXDxoYuEK10nPnprosuHkJdiiZjQ4SIXO02Egj8WFZoqDBYJ5GBRURkmdqpTW5B1Gr4kPOMFLdBnYd2iiudvFrvdVaIg0RStyFVXZ+3ouFW5sjX1jPB0a0Rl7K8id96Gt+sYgs0ROcmjosK7XhS25osoYHabPHp0XvKGlHmcAcqR9e9ugdlBkad8WXiFT6S/jaL0vTfRZTvgWFGavUV4sU1CmfcKxWxPwherdkU8Kmr+48UZwI+6oL9YGPh9Ih7f1Tm5k5L825SXVvslnhscKqo0QStyjVVPZ3Xpm8q1O7VrHarEZdjnkAcb1QmfPLKkfkwbPHp8XvKG9I/Ujqh4SVYBq8qhinhaTNzJokw9EOeJDz9R5FGbE+05qV1Z8p59otTYV7jlVvCQ+NiTdEysM3xelPjXC6V0duiXoasiwzFCfyNF/J4/VJyVaL6X/l/Qplx1ddaujluVK1tHuyueP5HaoyqeF5GF5/lqcV0ePT4v+RwpU/B4odB82HWsOIzdh99XMGoVHxHVuhtzff1TW1bizveXlTmr8JLUli34GSLOXScqQDtLaIo4Urjyg8KQyvBUJ89OFYt0jVgIZeFFHbnq6qwdHdeRa4VYkK/VcR1xqDCwWWvIqsT5CnBdHj0+L3mP9KAofQ/B1ALdHLEjLHZ43X04XiOKCEW8sKTvDfi62DHyFbXVqZ2ClxbGnC2M+IC4dZFhhPIwtK84YxiU6J8oPL8s8f6TuF7SihERJ9jHicS3qsiwX1wpKfvLDm2vT///pE256uqsiY6byPWQOHt5hShH5zEe7xKeJF/tG6n8fHKIuH3A4Tcu6vLo8XkpXhG6SChyYRr0d5GkjRMh3VcK9CvEQd9QHWPVO9IHrBc50UhR798v8qcdOdol4gzjnYlndndqpAhJ+oh8K389aQLmip1kc3p2gkgyh6Xx+coUkaddIbzKapE4FrFFJONFZGHdNSXP2kUTuerqrImOm+prqtjl54s5XyvWyHnpXZMdXh3+sMjPVgkj2Ss26YkiElguqnHt8GiClr+/aEgPinOYK8TdugnintHVwisVd/fOsESEceeLWHW7WIRzRbKex7OJ19Q0ZpI4/N0llLhQeMs87hT3xM4QCh0ovOUG4TkX6pgMZ+daR4iYtwx367gwRiY+VUWGdtFErro6a6LjpvraJqqBl4uq2hj8W3iRuSIfy2OlOMc8RXjGo4VHWSPmcrGO9/nq8miClr+/eNeuF73oRQP01DlSL3rxf4VeQ+pFL7oB/wOm+BUgbC39HwAAAABJRU5ErkJggg==\n",
|
||||
"text/latex": [
|
||||
"$\\displaystyle 1.0884335905187326$"
|
||||
"$\\displaystyle 0.983274288265642$"
|
||||
],
|
||||
"text/plain": [
|
||||
"1.0884335905187326"
|
||||
"0.983274288265642"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
|
|
@ -308,7 +297,20 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.6.9"
|
||||
"version": "3.8.5"
|
||||
},
|
||||
"toc": {
|
||||
"base_numbering": 1,
|
||||
"nav_menu": {},
|
||||
"number_sections": false,
|
||||
"sideBar": true,
|
||||
"skip_h1_title": true,
|
||||
"title_cell": "Table of Contents",
|
||||
"title_sidebar": "Contents",
|
||||
"toc_cell": false,
|
||||
"toc_position": {},
|
||||
"toc_section_display": true,
|
||||
"toc_window_display": false
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
|
|
|||
Различия файлов скрыты, потому что одна или несколько строк слишком длинны
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
Различия файлов скрыты, потому что одна или несколько строк слишком длинны
Различия файлов скрыты, потому что одна или несколько строк слишком длинны
|
|
@ -268,7 +268,7 @@
|
|||
}
|
||||
],
|
||||
"source": [
|
||||
"identified_estimand = model.identify_effect()\n",
|
||||
"identified_estimand = model.identify_effect(proceed_when_unidentifiable=True)\n",
|
||||
"print(identified_estimand)"
|
||||
]
|
||||
},
|
||||
|
|
|
|||
Различия файлов скрыты, потому что одна или несколько строк слишком длинны
Различия файлов скрыты, потому что одна или несколько строк слишком длинны
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
|
|
@ -136,7 +136,7 @@
|
|||
" treatment='treat',\n",
|
||||
" outcome='re78',\n",
|
||||
" common_causes='nodegr+black+hisp+age+educ+married'.split('+'))\n",
|
||||
"identified_estimand = model.identify_effect()\n",
|
||||
"identified_estimand = model.identify_effect(proceed_when_unidentifiable=True)\n",
|
||||
"estimate = model.estimate_effect(identified_estimand,\n",
|
||||
" method_name=\"backdoor.propensity_score_weighting\",\n",
|
||||
" method_params={\"weighting_scheme\":\"ips_weight\"})\n",
|
||||
|
|
|
|||
Различия файлов скрыты, потому что одна или несколько строк слишком длинны
Различия файлов скрыты, потому что одна или несколько строк слишком длинны
Различия файлов скрыты, потому что одна или несколько строк слишком длинны
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
Различия файлов скрыты, потому что одна или несколько строк слишком длинны
|
|
@ -20,8 +20,6 @@
|
|||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os, sys\n",
|
||||
"sys.path.append(os.path.abspath(\"../../../\"))\n",
|
||||
"import pandas as pd\n",
|
||||
"import numpy as np\n",
|
||||
"import dowhy\n",
|
||||
|
|
@ -418,27 +416,40 @@
|
|||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"INFO:dowhy.causal_identifier:Common causes of treatment and outcome:['gestat10', 'U']\n",
|
||||
"WARNING:dowhy.causal_identifier:If this is observed data (not from a randomized experiment), there might always be missing confounders. Causal effect cannot be identified perfectly.\n"
|
||||
"WARNING:dowhy.causal_identifier:If this is observed data (not from a randomized experiment), there might always be missing confounders. Causal effect cannot be identified perfectly.\n",
|
||||
"INFO:dowhy.causal_identifier:Continuing by ignoring these unobserved confounders because proceed_when_unidentifiable flag is True.\n",
|
||||
"INFO:dowhy.causal_identifier:Instrumental variables for treatment and outcome:[]\n",
|
||||
"INFO:dowhy.causal_identifier:Frontdoor variables for treatment and outcome:[]\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"WARN: Do you want to continue by ignoring any unobserved confounders? (use proceed_when_unidentifiable=True to disable this prompt) [y/n] y\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"INFO:dowhy.causal_identifier:Instrumental variables for treatment and outcome:[]\n"
|
||||
"Estimand type: nonparametric-ate\n",
|
||||
"\n",
|
||||
"### Estimand : 1\n",
|
||||
"Estimand name: backdoor1 (Default)\n",
|
||||
"Estimand expression:\n",
|
||||
" d \n",
|
||||
"────────────(Expectation(outcome|gestat10))\n",
|
||||
"d[treatment] \n",
|
||||
"Estimand assumption 1, Unconfoundedness: If U→{treatment} and U→outcome then P(outcome|treatment,gestat10,U) = P(outcome|treatment,gestat10)\n",
|
||||
"\n",
|
||||
"### Estimand : 2\n",
|
||||
"Estimand name: iv\n",
|
||||
"No such variable found!\n",
|
||||
"\n",
|
||||
"### Estimand : 3\n",
|
||||
"Estimand name: frontdoor\n",
|
||||
"No such variable found!\n",
|
||||
"\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"identified_estimand = model.identify_effect()"
|
||||
"identified_estimand = model.identify_effect(proceed_when_unidentifiable=True)\n",
|
||||
"print(identified_estimand)"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -464,8 +475,8 @@
|
|||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Linear Regression Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n"
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Linear Regression Estimator\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -474,29 +485,19 @@
|
|||
"text": [
|
||||
"*** Causal Estimate ***\n",
|
||||
"\n",
|
||||
"## Target estimand\n",
|
||||
"## Identified estimand\n",
|
||||
"Estimand type: nonparametric-ate\n",
|
||||
"### Estimand : 1\n",
|
||||
"Estimand name: backdoor\n",
|
||||
"Estimand expression:\n",
|
||||
" d \n",
|
||||
"────────────(Expectation(outcome|gestat10))\n",
|
||||
"d[treatment] \n",
|
||||
"Estimand assumption 1, Unconfoundedness: If U→{treatment} and U→outcome then P(outcome|treatment,gestat10,U) = P(outcome|treatment,gestat10)\n",
|
||||
"### Estimand : 2\n",
|
||||
"Estimand name: iv\n",
|
||||
"No such variable found!\n",
|
||||
"\n",
|
||||
"## Realized estimand\n",
|
||||
"b: outcome~treatment+gestat10\n",
|
||||
"## Estimate\n",
|
||||
"Value: -0.025200267022696315\n",
|
||||
"Target units: ate\n",
|
||||
"\n",
|
||||
"## Statistical Significance\n",
|
||||
"p-value: <0.001\n",
|
||||
"## Estimate\n",
|
||||
"Mean value: -0.025200267022700423\n",
|
||||
"p-value: [7.18902894e-08]\n",
|
||||
"\n",
|
||||
"ATE -0.025200267022696926\n",
|
||||
"Causal Estimate is -0.025200267022696315\n"
|
||||
"Causal Estimate is -0.025200267022700423\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -528,8 +529,8 @@
|
|||
"text": [
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/arshia/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" y = column_or_1d(y, warn=True)\n"
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -576,8 +577,8 @@
|
|||
"text": [
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10+w_random\n",
|
||||
"/home/arshia/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" y = column_or_1d(y, warn=True)\n"
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -585,8 +586,8 @@
|
|||
"output_type": "stream",
|
||||
"text": [
|
||||
"Refute: Add a Random Common Cause\n",
|
||||
"Estimated effect:(-0.012600133511348465,)\n",
|
||||
"New effect:(-0.02891355140186916,)\n",
|
||||
"Estimated effect:-0.012600133511348465\n",
|
||||
"New effect:-0.025826101468624834\n",
|
||||
"\n"
|
||||
]
|
||||
}
|
||||
|
|
@ -613,10 +614,89 @@
|
|||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"INFO:dowhy.causal_refuters.placebo_treatment_refuter:Refutation over 20 simulated datasets of permute treatment\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/arshia/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" y = column_or_1d(y, warn=True)\n"
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~placebo+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"WARNING:dowhy.causal_refuters.placebo_treatment_refuter:We assume a Normal Distribution as the sample has less than 100 examples.\n",
|
||||
" Note: The underlying distribution may not be Normal. We assume that it approaches normal with the increase in sample size.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -624,15 +704,17 @@
|
|||
"output_type": "stream",
|
||||
"text": [
|
||||
"Refute: Use a Placebo Treatment\n",
|
||||
"Estimated effect:(-0.012600133511348465,)\n",
|
||||
"New effect:(-0.16384345794392524,)\n",
|
||||
"Estimated effect:-0.012600133511348465\n",
|
||||
"New effect:0.06444843124165553\n",
|
||||
"p value:0.31698886663194925\n",
|
||||
"\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"res_placebo=model.refute_estimate(identified_estimand, estimate,\n",
|
||||
" method_name=\"placebo_treatment_refuter\", placebo_type=\"permute\")\n",
|
||||
" method_name=\"placebo_treatment_refuter\", placebo_type=\"permute\",\n",
|
||||
" num_simulations=20) \n",
|
||||
"print(res_placebo)"
|
||||
]
|
||||
},
|
||||
|
|
@ -652,10 +734,89 @@
|
|||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"INFO:dowhy.causal_refuters.data_subset_refuter:Refutation over 0.9 simulated datasets of size 21571.2 each\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/arshia/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" y = column_or_1d(y, warn=True)\n"
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"INFO:dowhy.causal_estimator:INFO: Using Propensity Score Matching Estimator\n",
|
||||
"INFO:dowhy.causal_estimator:b: outcome~treatment+gestat10\n",
|
||||
"/home/amit/py-envs/env3.8/lib/python3.8/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||
" return f(**kwargs)\n",
|
||||
"WARNING:dowhy.causal_refuters.data_subset_refuter:We assume a Normal Distribution as the sample has less than 100 examples.\n",
|
||||
" Note: The underlying distribution may not be Normal. We assume that it approaches normal with the increase in sample size.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -663,24 +824,19 @@
|
|||
"output_type": "stream",
|
||||
"text": [
|
||||
"Refute: Use a subset of data\n",
|
||||
"Estimated effect:(-0.012600133511348465,)\n",
|
||||
"New effect:(0.15136062305873627,)\n",
|
||||
"Estimated effect:-0.012600133511348465\n",
|
||||
"New effect:-0.08120856705762365\n",
|
||||
"p value:0.21986894766211718\n",
|
||||
"\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"res_subset=model.refute_estimate(identified_estimand, estimate,\n",
|
||||
" method_name=\"data_subset_refuter\", subset_fraction=0.9)\n",
|
||||
" method_name=\"data_subset_refuter\", subset_fraction=0.9,\n",
|
||||
" num_simulations=20)\n",
|
||||
"print(res_subset)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
|
|
|
|||
Различия файлов скрыты, потому что одна или несколько строк слишком длинны
Различия файлов скрыты, потому что одна или несколько строк слишком длинны
Различия файлов скрыты, потому что одна или несколько строк слишком длинны
|
|
@ -739,10 +739,11 @@ class CausalEstimate:
|
|||
s += "\n## Estimate\n"
|
||||
s += "Mean value: {0}\n".format(self.value)
|
||||
s += ""
|
||||
if hasattr(self, "cate_estimates"):
|
||||
s += "Effect estimates: {0}\n".format(self.cate_estimates)
|
||||
if self.estimator._significance_test:
|
||||
s += "p-value: {0}\n".format(self.estimator.signif_results_tostr(self.test_stat_significance()))
|
||||
if self.estimator._confidence_intervals:
|
||||
s += "Standard error: {0}\n".format(self.get_standard_error())
|
||||
s += "{0}% confidence interval: {1}\n".format(100 * self.estimator.confidence_level, self.get_confidence_intervals())
|
||||
if self.conditional_estimates is not None:
|
||||
s += "### Conditional Estimates\n"
|
||||
|
|
|
|||
|
|
@ -102,17 +102,24 @@ class Econml(CausalEstimator):
|
|||
est = self.estimator.effect(X_test, T0=T0_test, T1=T1_test)
|
||||
ate = np.mean(est)
|
||||
|
||||
est_interval = None
|
||||
self.effect_intervals = None
|
||||
if self._confidence_intervals:
|
||||
est_interval = self.estimator.effect_interval(X_test, T0=T0_test, T1=T1_test)
|
||||
self.effect_intervals = self.estimator.effect_interval(
|
||||
X_test, T0=T0_test, T1=T1_test,
|
||||
alpha=1-self.confidence_level)
|
||||
estimate = CausalEstimate(estimate=ate,
|
||||
target_estimand=self._target_estimand,
|
||||
realized_estimand_expr=self.symbolic_estimator,
|
||||
cate_estimates=est,
|
||||
effect_intervals=est_interval,
|
||||
effect_intervals=self.effect_intervals,
|
||||
_estimator_object=self.estimator)
|
||||
return estimate
|
||||
|
||||
def _estimate_confidence_intervals(self, confidence_level=None, method=None):
|
||||
""" Returns None if the confidence interval has not been calculated.
|
||||
"""
|
||||
return self.effect_intervals
|
||||
|
||||
def _do(self, x):
|
||||
raise NotImplementedError
|
||||
|
||||
|
|
|
|||
|
|
@ -11,31 +11,35 @@ from dowhy.utils.api import parse_state
|
|||
|
||||
|
||||
class CausalIdentifier:
|
||||
|
||||
"""Class that implements different identification methods.
|
||||
|
||||
Currently supports backdoor and instrumental variable identification methods. The identification is based on the causal graph provided.
|
||||
"""Class that implements different identification methods.
|
||||
|
||||
Other specific ways of identification, such as the ID* algorithm, minimal adjustment criteria, etc. will be added in the future.
|
||||
If you'd like to contribute, please raise an issue or a pull request on Github.
|
||||
Currently supports backdoor and instrumental variable identification methods. The identification is based on the causal graph provided.
|
||||
|
||||
Other specific ways of identification, such as the ID* algorithm, minimal adjustment criteria, etc. will be added in the future.
|
||||
If you'd like to contribute, please raise an issue or a pull request on Github.
|
||||
|
||||
"""
|
||||
NONPARAMETRIC_ATE="nonparametric-ate"
|
||||
NONPARAMETRIC_NDE="nonparametric-nde"
|
||||
NONPARAMETRIC_NIE="nonparametric-nie"
|
||||
MAX_BACKDOOR_ITERATIONS = 100000
|
||||
|
||||
def __init__(self, graph, estimand_type, proceed_when_unidentifiable=False):
|
||||
def __init__(self, graph, estimand_type,
|
||||
method_name = None,
|
||||
proceed_when_unidentifiable=False):
|
||||
self._graph = graph
|
||||
self.estimand_type = estimand_type
|
||||
self.treatment_name = graph.treatment_name
|
||||
self.outcome_name = graph.outcome_name
|
||||
self.method_name = method_name
|
||||
self._proceed_when_unidentifiable = proceed_when_unidentifiable
|
||||
self.logger = logging.getLogger(__name__)
|
||||
|
||||
def identify_effect(self):
|
||||
"""Main method that returns an identified estimand (if one exists).
|
||||
"""Main method that returns an identified estimand (if one exists).
|
||||
|
||||
If estimand_type is non-parametric ATE, then uses backdoor, instrumental variable and frontdoor identification methods, to check if an identified estimand exists, based on the causal graph.
|
||||
If estimand_type is non-parametric ATE, then uses backdoor, instrumental variable and frontdoor identification methods, to check if an identified estimand exists, based on the causal graph.
|
||||
|
||||
:param self: instance of the CausalEstimator class (or its subclass)
|
||||
:returns: target estimand, an instance of the IdentifiedEstimand class
|
||||
|
|
@ -226,8 +230,8 @@ class CausalIdentifier:
|
|||
)
|
||||
return estimand
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
def identify_backdoor(self, treatment_name, outcome_name):
|
||||
backdoor_sets = []
|
||||
|
|
@ -246,17 +250,39 @@ class CausalIdentifier:
|
|||
- set(outcome_name) \
|
||||
- set(self._graph.get_instruments(treatment_name, outcome_name))
|
||||
eligible_variables -= self._graph.get_descendants(treatment_name)
|
||||
for size_candidate_set in range(1, len(eligible_variables)+1):
|
||||
for candidate_set in itertools.combinations(eligible_variables, size_candidate_set):
|
||||
check = self._graph.check_valid_backdoor_set(treatment_name,
|
||||
outcome_name, candidate_set, backdoor_paths=backdoor_paths)
|
||||
self.logger.debug("Candidate backdoor set: {0}, is_dseparated: {1}, No. of paths blocked by observed_nodes: {2}".format(candidate_set, check["is_dseparated"], check["num_paths_blocked_by_observed_nodes"]))
|
||||
if check["is_dseparated"]:
|
||||
backdoor_sets.append({
|
||||
'backdoor_set': candidate_set,
|
||||
'num_paths_blocked_by_observed_nodes': check["num_paths_blocked_by_observed_nodes"]})
|
||||
|
||||
#causes_t = self._graph.get_causes(self.treatment_name)
|
||||
num_iterations = 0
|
||||
found_valid_adjustment_set = False
|
||||
if self.method_name == "auto":
|
||||
for size_candidate_set in range(len(eligible_variables), 0, -1):
|
||||
for candidate_set in itertools.combinations(eligible_variables, size_candidate_set):
|
||||
check = self._graph.check_valid_backdoor_set(treatment_name,
|
||||
outcome_name, candidate_set, backdoor_paths=backdoor_paths)
|
||||
self.logger.debug("Candidate backdoor set: {0}, is_dseparated: {1}, No. of paths blocked by observed_nodes: {2}".format(candidate_set, check["is_dseparated"], check["num_paths_blocked_by_observed_nodes"]))
|
||||
if check["is_dseparated"]:
|
||||
backdoor_sets.append({
|
||||
'backdoor_set': candidate_set,
|
||||
'num_paths_blocked_by_observed_nodes': check["num_paths_blocked_by_observed_nodes"]})
|
||||
if self._graph.all_observed(candidate_set):
|
||||
found_valid_adjustment_set = True
|
||||
num_iterations += 1
|
||||
if num_iterations > CausalIdentifier.MAX_BACKDOOR_ITERATIONS:
|
||||
break
|
||||
if found_valid_adjustment_set:
|
||||
break
|
||||
elif self.method_name == "exhaustive-search":
|
||||
for size_candidate_set in range(1, len(eligible_variables)+1):
|
||||
for candidate_set in itertools.combinations(eligible_variables, size_candidate_set):
|
||||
check = self._graph.check_valid_backdoor_set(treatment_name,
|
||||
outcome_name, candidate_set, backdoor_paths=backdoor_paths)
|
||||
self.logger.debug("Candidate backdoor set: {0}, is_dseparated: {1}, No. of paths blocked by observed_nodes: {2}".format(candidate_set, check["is_dseparated"], check["num_paths_blocked_by_observed_nodes"]))
|
||||
if check["is_dseparated"]:
|
||||
backdoor_sets.append({
|
||||
'backdoor_set': candidate_set,
|
||||
'num_paths_blocked_by_observed_nodes': check["num_paths_blocked_by_observed_nodes"]})
|
||||
else:
|
||||
raise ValueError("Identifier method " + self.method_name + "not supported. Try 'default' or 'exhaustive-search'.")
|
||||
#causes_t = self._graph.get_causes(self.treatment_name)
|
||||
#causes_y = self._graph.get_causes(self.outcome_name, remove_edges={'sources':self.treatment_name, 'targets':self.outcome_name})
|
||||
#common_causes = list(causes_t.intersection(causes_y))
|
||||
#self.logger.info("Common causes of treatment and outcome:" + str(common_causes))
|
||||
|
|
@ -265,7 +291,7 @@ class CausalIdentifier:
|
|||
return backdoor_sets
|
||||
else:
|
||||
return observed_backdoor_sets
|
||||
|
||||
|
||||
def get_default_backdoor_set_id(self, backdoor_sets_dict):
|
||||
# Adding a None estimand if no backdoor set found
|
||||
if len(backdoor_sets_dict) == 0:
|
||||
|
|
@ -279,7 +305,7 @@ class CausalIdentifier:
|
|||
default_key = key
|
||||
return default_key
|
||||
|
||||
def build_backdoor_estimands_dict(self, treatment_name, outcome_name,
|
||||
def build_backdoor_estimands_dict(self, treatment_name, outcome_name,
|
||||
backdoor_sets, estimands_dict, proceed_when_unidentifiable=None):
|
||||
backdoor_variables_dict = {}
|
||||
if proceed_when_unidentifiable is None:
|
||||
|
|
@ -321,11 +347,11 @@ class CausalIdentifier:
|
|||
estimands_dict["backdoor"+str(i+1)] = backdoor_estimand_expr
|
||||
backdoor_variables_dict["backdoor"+str(i+1)] = backdoor_sets_arr[i]
|
||||
return estimands_dict, backdoor_variables_dict
|
||||
|
||||
def identify_frontdoor(self):
|
||||
""" Find a valid frontdoor variable if it exists.
|
||||
|
||||
Currently only supports a single variable frontdoor set.
|
||||
def identify_frontdoor(self):
|
||||
""" Find a valid frontdoor variable if it exists.
|
||||
|
||||
Currently only supports a single variable frontdoor set.
|
||||
"""
|
||||
frontdoor_var = None
|
||||
frontdoor_paths = self._graph.get_all_directed_paths(self.treatment_name, self.outcome_name)
|
||||
|
|
@ -342,9 +368,9 @@ class CausalIdentifier:
|
|||
return parse_state(frontdoor_var)
|
||||
|
||||
def identify_mediation(self):
|
||||
""" Find a valid mediator if it exists.
|
||||
""" Find a valid mediator if it exists.
|
||||
|
||||
Currently only supports a single variable mediator set.
|
||||
Currently only supports a single variable mediator set.
|
||||
"""
|
||||
mediation_var = None
|
||||
mediation_paths = self._graph.get_all_directed_paths(self.treatment_name, self.outcome_name)
|
||||
|
|
@ -407,7 +433,7 @@ class CausalIdentifier:
|
|||
max_set_length = len(bdoor_set)
|
||||
default_key = key
|
||||
return default_key
|
||||
|
||||
|
||||
def construct_backdoor_estimand(self, estimand_type, treatment_name,
|
||||
outcome_name, common_causes):
|
||||
# TODO: outputs string for now, but ideally should do symbolic
|
||||
|
|
@ -550,7 +576,7 @@ class CausalIdentifier:
|
|||
|
||||
class IdentifiedEstimand:
|
||||
|
||||
"""Class for storing a causal estimand, typically as a result of the identification step.
|
||||
"""Class for storing a causal estimand, typically as a result of the identification step.
|
||||
|
||||
"""
|
||||
|
||||
|
|
@ -582,8 +608,8 @@ class IdentifiedEstimand:
|
|||
def get_backdoor_variables(self, key=None):
|
||||
""" Return a list containing the backdoor variables.
|
||||
|
||||
If the calling estimator method is a backdoor method, return the
|
||||
backdoor variables corresponding to its target estimand.
|
||||
If the calling estimator method is a backdoor method, return the
|
||||
backdoor variables corresponding to its target estimand.
|
||||
Otherwise, return the backdoor variables for the default backdoor estimand.
|
||||
"""
|
||||
if key is None:
|
||||
|
|
|
|||
|
|
@ -126,7 +126,8 @@ class CausalModel:
|
|||
self._other_variables = kwargs
|
||||
self.summary()
|
||||
|
||||
def identify_effect(self, estimand_type=None, proceed_when_unidentifiable=None):
|
||||
def identify_effect(self, estimand_type=None,
|
||||
method_name="auto", proceed_when_unidentifiable=None):
|
||||
"""Identify the causal effect to be estimated, using properties of the causal graph.
|
||||
|
||||
:param proceed_when_unidentifiable: Binary flag indicating whether identification should proceed in the presence of (potential) unobserved confounders.
|
||||
|
|
@ -140,6 +141,7 @@ class CausalModel:
|
|||
|
||||
self.identifier = CausalIdentifier(self._graph,
|
||||
estimand_type,
|
||||
method_name,
|
||||
proceed_when_unidentifiable=proceed_when_unidentifiable)
|
||||
identified_estimand = self.identifier.identify_effect()
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,75 @@
|
|||
import os
|
||||
import subprocess
|
||||
import tempfile
|
||||
|
||||
import nbformat
|
||||
import pytest
|
||||
|
||||
NOTEBOOKS_PATH = "docs/source/example_notebooks/"
|
||||
notebooks_list = [ f.name for f in os.scandir(NOTEBOOKS_PATH) if f.name.endswith(".ipynb")]
|
||||
advanced_notebooks = [
|
||||
# requires stdin input for identify in weighting sampler
|
||||
"do_sampler_demo.ipynb",
|
||||
# requires Rpy2 for lalonde
|
||||
"dowhy_refutation_testing.ipynb",
|
||||
"dowhy_lalonde_example.ipynb",
|
||||
"lalonde_pandas_api.ipynb",
|
||||
# very slow
|
||||
"dowhy-conditional-treatment-effects.ipynb",
|
||||
"dowhy_refuter_notebook.ipynb",
|
||||
"DoWhy-The Causal Story Behind Hotel Booking Cancellations.ipynb", # needs xgboost too
|
||||
]
|
||||
|
||||
# Adding the dowhy root folder to the python path so that jupyter notebooks
|
||||
# can import dowhy
|
||||
if 'PYTHONPATH' not in os.environ:
|
||||
os.environ['PYTHONPATH'] = os.getcwd()
|
||||
elif os.getcwd() not in os.environ['PYTHONPATH'].split(os.pathsep):
|
||||
os.environ['PYTHONPATH'] = os.environ['PYTHONPATH'] + os.pathsep + os.getcwd()
|
||||
|
||||
def _notebook_run(filepath):
|
||||
"""Execute a notebook via nbconvert and collect output.
|
||||
:returns (parsed nb object, execution errors)
|
||||
|
||||
Source of this function: http://www.christianmoscardi.com/blog/2016/01/20/jupyter-testing.html
|
||||
"""
|
||||
with tempfile.NamedTemporaryFile(suffix=".ipynb") as fout:
|
||||
args = ["jupyter", "nbconvert", "--to", "notebook", "--execute",
|
||||
# "--ExecutePreprocessor.timeout=600",
|
||||
"-y", "--no-prompt",
|
||||
"--output", fout.name, filepath]
|
||||
subprocess.check_call(args)
|
||||
|
||||
fout.seek(0)
|
||||
nb = nbformat.read(fout, nbformat.current_nbformat)
|
||||
|
||||
errors = [output for cell in nb.cells if "outputs" in cell
|
||||
for output in cell["outputs"]\
|
||||
if output.output_type == "error"]
|
||||
|
||||
return nb, errors
|
||||
|
||||
"""
|
||||
def test_getstarted_notebook():
|
||||
nb, errors = _notebook_run(NOTEBOOKS_PATH+ "dowhy_simple_example.ipynb")
|
||||
assert errors == []
|
||||
|
||||
def test_confounder_notebook():
|
||||
nb, errors = _notebook_run(NOTEBOOKS_PATH+"dowhy_confounder_example.ipynb")
|
||||
assert errors = []
|
||||
"""
|
||||
parameter_list=[]
|
||||
for nb in notebooks_list:
|
||||
if nb in advanced_notebooks:
|
||||
param = pytest.param(nb,
|
||||
marks=[pytest.mark.skip, pytest.mark.advanced],
|
||||
id=nb)
|
||||
else:
|
||||
param = pytest.param(nb, id=nb)
|
||||
parameter_list.append(param)
|
||||
|
||||
@pytest.mark.parametrize("notebook_filename", parameter_list)
|
||||
def test_notebook(notebook_filename):
|
||||
nb, errors = _notebook_run(NOTEBOOKS_PATH + notebook_filename)
|
||||
assert errors == []
|
||||
|
||||
Загрузка…
Ссылка в новой задаче