Merge pull request #65 from UBC-MDS/milestone-2-fix

Milestone 2 fix

.gitignore

@@ -1,4 +1,4 @@
-/.ipynb_checkpoints
+*.ipynb_checkpoints
 /analysis/.ipynb_checkpoints/
 /report/.ipynb_checkpoints/
 /results/figures/.ipynb_checkpoints

Dockerfile

@@ -8,9 +8,6 @@ USER root
 RUN sudo apt update \
     && sudo apt install -y lmodern
 
-RUN sudo apt-get update \
-    && sudo apt-get install -y make
-
 USER $NB_UID
 
 RUN mamba update --quiet --file /tmp/conda-linux-64.lock \

README.md

@@ -74,20 +74,20 @@ where you launched the container, and then type `docker compose rm`
 ```
    python scripts/download.py \
       --id 186 \
-      --save_to ./data/wine.csv
+      --save_to ./data/raw/wine.csv
 
    python scripts/clean_n_split_data.py \
-      --raw-data ./data/wine.csv
+      --raw-data ./data/raw/wine.csv
 
    python scripts/validation_before_split.py \
       --file_name wine.csv \
-      --data_path ./data/
+      --data_path ./data/raw
 
 ```
 4.2 Run EDA
 ```
    python scripts/eda_n_correlation_check.py \
-      --train-file ./data/wine_train.csv \
+      --train-file ./data/proc/wine_train.csv \
       --output-img ./results/figures \
       --output-table ./results/tables
 ```
@@ -97,8 +97,8 @@ where you launched the container, and then type `docker compose rm`
       --pipe-to ./results/models
 
    python scripts/model_evaluation_wine_predictor.py \
-      --train-data ./data/wine_train.csv \
-      --test-data ./data/wine_test.csv \
+      --train-data ./data/proc/wine_train.csv \
+      --test-data ./data/proc/wine_test.csv \
       --pipeline-path ./results/models/wine_pipeline.pickle \
       --table-to ./results/tables \
       --plot-to ./results/figures
@@ -109,5 +109,8 @@ where you launched the container, and then type `docker compose rm`
    quarto render report/report.qmd --to pdf
 ```
 
+# License
+This project was created with the [`MIT License`](LICENSE.md)
+
 # References
 Cortez P, Cerdeira A, Almeida F, Matos T, Reis J. Wine Quality [dataset]. 2009. UCI Machine Learning Repository. Available from: https://doi.org/10.24432/C56S3T.

docker-compose.yml

@@ -4,8 +4,8 @@ services:
     ports:
       - "8888:8888" 
     volumes:
-      - "${PWD}:/app/data"
-    working_dir: /app
+      - "${PWD}:/app/data" 
+    working_dir: /app/data
     deploy:
       resources:
         limits:

results/tables/random_search.csv

@@ -2,4 +2,4 @@
 mean_train_score,0.9875779986984037,0.9873192686470664,0.9887321572718368,0.9882197254580379,0.9883474962027348,0.9870566844281605,0.9880919482052322,0.9870566844281605,0.9864183082552028,0.9861637573491556
 mean_test_score,0.9885928776559425,0.9885928776559425,0.9885821459956146,0.988576762777796,0.988576762777796,0.9880680139186435,0.9880653223097344,0.9870318213202898,0.9855028900889848,0.9844799953502902
 param_logisticregression__C,1.2665709946616681,0.9159332036121722,9.15226100278092,2.4713734184878824,2.74750150868112,0.7017992831138442,2.342391466254441,0.6084642077147051,0.37348973478010344,0.28425159292991603
-mean_fit_time,0.8944474697113037,0.623142671585083,0.9552007675170898,1.446831512451172,0.8496040344238281,0.7155133247375488,0.9875524997711181,0.5591573238372802,1.4225006580352784,0.7792784214019776
+mean_fit_time,0.4468091487884521,0.40517253875732423,0.6185922622680664,0.7212271690368652,0.47739248275756835,0.5206932544708252,0.590698528289795,0.40631418228149413,0.6384647846221924,0.5607413291931153

tests/README

@@ -3,4 +3,6 @@ pytest -v test_random_search.py \
     --test_data=../data/proc/wine_test.csv \
     --pipeline_path=../results/models/wine_pipeline.pickle
 
-pytest test_validate_column_names.py 
+pytest test_validate_column_names.py 
+
+pytest test_split_data.py