Thesis Submission (#8)

State of the project at submission of thesis in November.

.github/workflows/main.yml

@@ -4,40 +4,50 @@ name: main
 concurrency:
   group: ${{ github.head_ref || github.run_id }}
   cancel-in-progress: true
-# yamllint disable-line rule:truthy
+# yamllint disable rule:line-length
 on:
   push:
     branches: [main]
   pull_request:
-    branches: ['*']
+    branches: ["*"]
 jobs:
   run-tests:
     name: Run tests for ${{ matrix.os }} on ${{ matrix.python-version }}
     runs-on: ${{ matrix.os }}
     strategy:
       fail-fast: false
       matrix:
-        # Currently only developing on windows.
-        os: [windows-latest]
         # os: [ubuntu-latest, macos-latest, windows-latest]
-        python-version: ['3.12']
+        os: [windows-latest]
+        python-version: ["3.12"]
     steps:
-      - uses: actions/checkout@v3
-      - name: create build environment
-        uses: mamba-org/provision-with-micromamba@main
+      - uses: actions/checkout@v4
+      - name: Install TinyTex
+        uses: r-lib/actions/setup-tinytex@v2
+      - name: Install additional LaTeX packages
+        run: |
+          tlmgr update --self
+          tlmgr install a4wide beamer biber biblatex caption eurosym grfext minibox moreverb ntgclass relsize setspace xfrac
+          tlmgr list --only-installed
+      - name: Install conda environment with micromamba
+        uses: mamba-org/setup-micromamba@v1
         with:
           environment-file: environment.yml
-          environment-name: gha-testing
-          cache-env: true
-          extra-specs: |
-            python=${{ matrix.python-version }}
-      - name: run pytest
+          create-args: python=${{ matrix.python-version }}
+          cache-environment: true
+          micromamba-version: 1.5.6-0
+      - name: Run full test suite on MacOS and Linux
+        shell: bash -l {0}
+        run: |
+          micromamba activate thesis
+          pytest -v --cov=./ --cov-report=xml
+        if: runner.os != 'Windows'
+      - name: Run test suite on Windows
         shell: bash -l {0}
         run: |
-          micromamba activate gha-testing
-          pytest --cov-report=xml --cov=./
-      - name: Upload coverage report.
-        if: runner.os == 'Linux' && matrix.python-version == '3.12'
+          micromamba activate thesis
+          pytest -v --cov=./ --cov-report=xml
+        if: runner.os == 'Windows'
+      - name: Upload coverage reports
+        if: runner.os == 'Windows' && matrix.python-version == '3.12'
         uses: codecov/codecov-action@v3
-        # with:
-        #   token: ${{ secrets.CODECOV_TOKEN }}

.gitignore

@@ -10,7 +10,7 @@
 .pytask
 
 # bld
-bld/
+/bld/
 
 # latex
 *.aux
@@ -28,6 +28,8 @@ bld/
 *.toc
 *.snm
 *.nav
+*.lof
+*.lot
 
 # Jupyter notebooks
 *.ipynb

.pre-commit-config.yaml

@@ -15,7 +15,7 @@ repos:
     rev: v4.4.0
     hooks:
       - id: check-added-large-files
-        args: [--maxkb=25]
+        args: [--maxkb=5000]
       - id: check-case-conflict
       - id: check-merge-conflict
       - id: check-vcs-permalinks

.vscode/ltex.dictionary.en-US.txt

@@ -0,0 +1,56 @@
+Budde
+MTE
+complier
+compliers
+instrument-compliers
+complier-LATE
+LATEs
+subsampling
+monotonicity
+DGPs
+MTRs
+Subsampling
+estimand
+linprog
+estimands
+Monotonicity
+
+covariates
+functionals
+OLS
+Slutsky
+Hadamard
+MSTs
+misspecified
+
+Estimands
+Complier
+TODO
+optimagic
+COBYLA
+Imbens-Manski
+reparameterization
+
+nonparametric
+Nonparametric
+
+subsample
+Ivmte
+Bei
+Econometrica
+Compliers
+nondifferentiable
+RDD
+DiD
+
+exogenously
+piecewise
+
+pyvmte
+Pyvmte
+ivmte
+Gurobi
+
+Freyberger
+Rheinische
+Friedrich-Wilhelms-Universität

.vscode/ltex.hiddenFalsePositives.en-US.txt

@@ -0,0 +1,21 @@
+{"rule":"UPPERCASE_SENTENCE_START","sentence":"^\\Qbreaklines=true, postbreak=, numbers=left, numbersep=5pt, numberstyle=, basicstyle=\\E$"}
+{"rule":"MORFOLOGIK_RULE_EN_US","sentence":"^\\Qbreaklines=true, postbreak=, numbers=left, numbersep=5pt, numberstyle=, basicstyle=\\E$"}
+{"rule":"WHITESPACE_RULE","sentence":"^\\Qver@etex.sty3000/12/31\\E$"}
+{"rule":"MORFOLOGIK_RULE_EN_US","sentence":"^\\Qcompat=1.18\\E$"}
+
+{"rule":"MASS_AGREEMENT","sentence":"^\\QMST maintain the following assumptions, which guarantee a \"valid\" instrument\\E$"}
+{"rule":"MASS_AGREEMENT","sentence":"^\\QMST maintain the following assumptions, which guarantee a “valid” instrument\\E$"}
+{"rule":"HE_VERB_AGR","sentence":"^\\QTo address this, MST propose a two-way estimator that is guaranteed to exist.\\E$"}
+{"rule":"NO_COMMA_BEFORE_INDIRECT_QUESTION","sentence":"^\\QIn particular, we know \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q, where \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q is easy to estimate.\\E$"}
+{"rule":"MORFOLOGIK_RULE_EN_US","sentence":"^\\QOne potential source of information could be solving the estimation problem at hand under increasing relaxations as well as comparing the degree of conservativeness to an initial (biased) bootstrap estimate of the standard error.\\E$"}
+
+{"rule":"IF_IS","sentence":"^\\QThe directional derivative in our case is given by \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q if \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q if \\E(?:Dummy|Ina|Jimmy-)[0-9]+$"}
+{"rule":"IF_IS","sentence":"^\\QThe directional derivative in our case is given by \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q if \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q if \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q if \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q.\\E$"}
+{"rule":"IF_IS","sentence":"^\\QIn particular, consider the estimator \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q if \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q if \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q if \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q.\\E$"}
+{"rule":"IF_IS","sentence":"^\\QIn particular, consider the estimator \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q if \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q if \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q if \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q, where \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q is an estimator of the asymptotic standard deviation of \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q.\\E$"}
+{"rule":"IF_IS","sentence":"^\\QHence, I construct the following estimator which takes into account both variability in estimating \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q and \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q: \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q if \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q if \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q if \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q.\\E$"}
+
+{"rule":"IF_IS","sentence":"^\\QThe directional derivative for our case when \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q is known is given by \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q if \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q if \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q if \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q.\\E$"}
+{"rule":"EN_A_VS_AN","sentence":"^\\QI report results for a lower-order, and hence more restrictive polynomial of degree \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q as well as an \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Qth order polynomial similar to the numerical example in \\E(?:Dummy|Ina|Jimmy-)[0-9]+\\Q.\\E$"}
+
+{"rule":"MASS_AGREEMENT","sentence":"^\\QMST provide no distributional results.\\E$"}

compress_dir.sh

@@ -0,0 +1,27 @@
+#!/bin/bash
+# A bash script to copy results from marvin for a specific job.
+# Usage: ./copy_from_marvin.sh <job_id>
+# The script will create a directory with the job_id and copy the results from marvin
+# to that directory.
+
+if [ "$#" -ne 1 ]; then
+    echo "Usage: $0 <job_id>"
+    exit 1
+fi
+
+JOBID=$1
+USER=s93jbudd_hpc
+
+DATE=$(date +%d-%m-%Y" "%H:%M:%S)
+
+DIR_SOURCE="./marvin/$JOBID"
+
+cd C:/Users/budde/projects/thesis/src/thesis/ || exit
+
+# Create a directory with the job_id
+mkdir -p $DIR_SOURCE
+
+# Compress
+tar -czf $DIR_SOURCE.tar.gz $DIR_SOURCE
+
+echo "[$DATE] Results compressed: $JOBID"

copy_from_marvin.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+# A bash script to copy results from marvin for a specific job.
+# Usage: ./copy_from_marvin.sh <job_id>
+# The script will create a directory with the job_id and copy the results from marvin
+# to that directory.
+
+if [ "$#" -ne 1 ]; then
+    echo "Usage: $0 <job_id>"
+    exit 1
+fi
+
+JOBID=$1
+USER=s93jbudd_hpc
+
+DATE=$(date +%d-%m-%Y" "%H:%M:%S)
+
+DIR_TARGET="./marvin/$JOBID"
+
+cd C:/Users/budde/projects/thesis/src/thesis/ || exit
+
+# Create a directory with the job_id
+mkdir -p $DIR_TARGET
+
+# Copy the results from marvin
+scp -r -C $USER@marvin.hpc.uni-bonn.de:/lustre/scratch/data/$USER-thesis/thesis/bld/ $DIR_TARGET

copy_from_marvin_v2.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+# A bash script to copy results from marvin for a specific job.
+# Usage: ./copy_from_marvin.sh <job_id>
+# The script will create a directory with the job_id and copy the results from marvin
+# to that directory.
+
+if [ "$#" -ne 1 ]; then
+    echo "Usage: $0 <job_id>"
+    exit 1
+fi
+
+JOBID=$1
+USER=s93jbudd_hpc
+
+DATE=$(date +%d-%m-%Y" "%H:%M:%S)
+
+DIR_TARGET="./marvin/$JOBID"
+
+cd C:/Users/budde/projects/thesis/src/thesis/ || exit
+
+# Create a directory with the job_id
+mkdir -p $DIR_TARGET
+
+# Copy the results from marvin
+scp -r -C $USER@marvin.hpc.uni-bonn.de:/lustre/scratch/data/$USER-thesis/thesis_v2/thesis/bld/ $DIR_TARGET

environment.yml

@@ -21,24 +21,15 @@ dependencies:
 
   # Python template project dependencies
   - statsmodels
-  - numpy
+  - numpy >= 2.0
   - pandas >=2.2
   - plotly >=5.2.0,<6
 
-  # R template project dependencies
-  # Currently we are not using R hence we do not need to install these dependencies.
-  # - pytask-r >=0.4.1
-  # - pyreadr
-  # - r-plyr
-  # - r-precommit
-  # - r-yaml
-  # - r-forcats
-
   # Install project
   - pip:
     - -e .
     - pdbp
-    - kaleido==0.1.0.post1
+    - kaleido
     - joblib
-    - git+https://github.com/buddejul/pyvmte
+    - git+https://github.com/buddejul/pyvmte@im_crit
     - coptpy