IUM_12

.dvc/.gitignore

@@ -0,0 +1,3 @@
+/config.local
+/tmp
+/cache

.dvc/config

@@ -0,0 +1,4 @@
+[core]
+    remote = ium_ssh_remote
+['remote "ium_ssh_remote"']
+    url = ssh://ium-sftp@tzietkiewicz.vm.wmi.amu.edu.pl

.dvcignore

@@ -0,0 +1,3 @@
+# Add patterns of files dvc should ignore, which could improve
+# the performance. Learn more at
+# https://dvc.org/doc/user-guide/dvcignore

.gitignore

@@ -0,0 +1,4 @@
+/beer_reviews_train.csv
+/beer_reviews_test.csv
+/beer_review_sentiment_model.h5
+/beer_review_sentiment_predictions.csv

Dockerfile

@@ -8,9 +8,9 @@ ARG DEBIAN_FRONTEND=noninteractive
 ENV TZ=Etc/UTC
 
 RUN apt update && \
-    apt install -y python3 python3-pip unzip
+    apt install -y python3 python3-pip unzip git
 
-RUN pip install kaggle pandas seaborn scikit-learn tensorflow
+RUN pip install kaggle pandas seaborn scikit-learn tensorflow sacred pymongo --break-system-packages
 
 WORKDIR /app
 

IUM_02.py

@@ -22,6 +22,7 @@ api.dataset_download_files('thedevastator/1-5-million-beer-reviews-from-beer-adv
 #
 # get_ipython().system('kaggle datasets download -d thedevastator/1-5-million-beer-reviews-from-beer-advocate')
 #
+#Change
 #
 # # In[ ]:
 #

IUM_05-predict.py

@@ -1,18 +1,18 @@
 import pandas as pd
-import numpy as np
 import tensorflow as tf
 
 test_data = pd.read_csv('./beer_reviews_test.csv')
 X_test = test_data[['review_aroma', 'review_appearance', 'review_palate', 'review_taste']]
+y_test = test_data['review_overall']
 
 model = tf.keras.models.load_model('beer_review_sentiment_model.h5')
 
-tokenizer = tf.keras.preprocessing.text.Tokenizer(num_words=10000)
+predictions = model.predict(X_test)
 
+print(f'Predictions shape: {predictions.shape}')
 
-X_test_seq = tokenizer.texts_to_sequences(X_test)
+if len(predictions.shape) > 1:
-X_test_pad = tf.keras.preprocessing.sequence.pad_sequences(X_test_seq, maxlen=100)
+    predictions = predictions[:, 0]
 
-predictions = model.predict(X_test_pad)
+results = pd.DataFrame({'Predictions': predictions, 'Actual': y_test})
-
+results.to_csv('beer_review_sentiment_predictions.csv', index=False)
-np.savetxt('beer_review_sentiment_predictions.csv', predictions, delimiter=',', fmt='%.10f')

IUM_05-split.py

@@ -1,7 +1,7 @@
 import pandas as pd
 from sklearn.model_selection import train_test_split
 
-data = pd.read_csv('./beer_reviews.csv')
+data = pd.read_csv('beer_reviews.csv')
 
 train_data, test_data = train_test_split(data, test_size=0.2, random_state=42)
 

Jenkinsfile

@@ -1,25 +1,36 @@
 pipeline {
     agent any
 
-    triggers {
-        upstream(upstreamProjects: 'z-s464979-create-dataset', threshold: hudson.model.Result.SUCCESS)
-    }
-
     parameters {
-        string(name: 'EPOCHS', defaultValue: '40', description: 'Number of epochs')
+        string(name: 'CUTOFF', defaultValue: '10000', description: 'Liczba wierszy do obcięcia ze zbioru danych')
-        string(name: 'BATCH_SIZE', defaultValue: '32', description: 'Batch size')
+	    string(name: 'KAGGLE_USERNAME', defaultValue: '', description: 'Kaggle username')
-        buildSelector(defaultSelector: lastSuccessful(), description: 'Which build to use for copying artifacts', name: 'BUILD_SELECTOR')
+        password(name: 'KAGGLE_KEY', defaultValue: '', description: 'Kaggle API key')
     }
 
     stages {
         stage('Clone Repository') {
             steps {
-                git branch: 'training', url: "https://git.wmi.amu.edu.pl/s464979/ium_464979.git"
+                git url: "https://git.wmi.amu.edu.pl/s464979/ium_464979"
             }
         }
-        stage('Copy Artifacts') {
+        stage('Download dataset') {
             steps {
-                 copyArtifacts filter: 'beer_reviews.csv,beer_reviews_train.csv,beer_reviews_test.csv', projectName: 'z-s464979-create-dataset', selector: buildParameter('BUILD_SELECTOR')
+                 withEnv(["KAGGLE_USERNAME=${env.KAGGLE_USERNAME}", "KAGGLE_KEY=${env.KAGGLE_KEY}"]) {
+                    sh "kaggle datasets download -d thedevastator/1-5-million-beer-reviews-from-beer-advocate --unzip"
+                }
+            }
+        }
+        stage('Process and Split Dataset') {
+            agent {
+                dockerfile {
+                    filename 'Dockerfile'
+                    reuseNode true
+                }
+            }
+            steps {
+                sh "chmod +x ./IUM_05-split.py"
+                sh "python3 ./IUM_05-split.py"
+                archiveArtifacts artifacts: 'beer_reviews.csv,beer_reviews_train.csv,beer_reviews_test.csv', onlyIfSuccessful: true
             }
         }
         stage("Run") {
@@ -31,8 +42,29 @@ pipeline {
             }
             steps {
                 sh "chmod +x ./IUM_05-model.py"
-                sh "python3 ./IUM_05-model.py ${params.EPOCHS} ${params.BATCH_SIZE}"
+                sh "chmod +x ./IUM_05-predict.py"
-                archiveArtifacts artifacts: 'beer_review_sentiment_model.h5', onlyIfSuccessful: true
+                sh "python3 ./IUM_05-model.py 10 32"
+                sh "python3 ./IUM_05-predict.py"
+                archiveArtifacts artifacts: 'beer_review_sentiment_model.h5,beer_review_sentiment_predictions.csv', onlyIfSuccessful: true
+            }
+        }
+
+        stage('Sacred') {
+            agent {
+                dockerfile {
+                    filename 'Dockerfile'
+                    reuseNode true
+                }
+            }
+            steps {
+               sh 'chmod +x sacred/sacred_training_model.py'
+               sh 'python3 sacred/sacred_training_model.py'
+            }
+        }
+
+        stage('Archive Artifacts from Experiments') {
+          steps {
+            archiveArtifacts artifacts: 'sacred_runs/**/*.*', onlyIfSuccessful: true
           }
         }
     }

data/.gitignore

@@ -0,0 +1 @@
+/beer_reviews.csv

data/beer_reviews.csv.dvc

@@ -0,0 +1,5 @@
+outs:
+- md5: 50f6eec0d0fe78bc0f10e35edd271998
+  size: 201644905
+  hash: md5
+  path: beer_reviews.csv

dvc.lock

@@ -0,0 +1,46 @@
+schema: '2.0'
+stages:
+  split_data:
+    cmd: python IUM_05-split.py
+    deps:
+    - path: data/beer_reviews.csv
+      hash: md5
+      md5: 50f6eec0d0fe78bc0f10e35edd271998
+      size: 201644905
+    outs:
+    - path: beer_reviews_test.csv
+      hash: md5
+      md5: edbd0a7f05c59a0c0e936917f60e9b96
+      size: 40632354
+    - path: beer_reviews_train.csv
+      hash: md5
+      md5: 8c6877a26fef1542369bfae6b39d163c
+      size: 162599343
+  train_model:
+    cmd: python IUM_05-model.py 10 32
+    deps:
+    - path: beer_reviews_train.csv
+      hash: md5
+      md5: 8c6877a26fef1542369bfae6b39d163c
+      size: 162599343
+    outs:
+    - path: beer_review_sentiment_model.h5
+      hash: md5
+      md5: c126bd5d332a905262c66894585450e3
+      size: 1950856
+  predict:
+    cmd: python IUM_05-predict.py
+    deps:
+    - path: beer_review_sentiment_model.h5
+      hash: md5
+      md5: c126bd5d332a905262c66894585450e3
+      size: 1950856
+    - path: beer_reviews_test.csv
+      hash: md5
+      md5: edbd0a7f05c59a0c0e936917f60e9b96
+      size: 40632354
+    outs:
+    - path: beer_review_sentiment_predictions.csv
+      hash: md5
+      md5: 12a66fafb7f4d7d19eb0c4a90cc7d3ad
+      size: 4814242

dvc.yaml

@@ -0,0 +1,23 @@
+stages:
+  split_data:
+    cmd: python IUM_05-split.py
+    deps:
+      - data/beer_reviews.csv
+    outs:
+      - beer_reviews_train.csv
+      - beer_reviews_test.csv
+
+  train_model:
+    cmd: python IUM_05-model.py 10 32
+    deps:
+      - beer_reviews_train.csv
+    outs:
+      - beer_review_sentiment_model.h5
+
+  predict:
+    cmd: python IUM_05-predict.py
+    deps:
+      - beer_review_sentiment_model.h5
+      - beer_reviews_test.csv
+    outs:
+      - beer_review_sentiment_predictions.csv

environment.yml

@@ -0,0 +1,338 @@
+name: uczenie_glebokie
+channels:
+  - conda-forge
+  - defaults
+dependencies:
+  - _tflow_select=2.3.0=mkl
+  - abseil-cpp=20211102.0=h36ffca9_3
+  - absl-py=2.1.0=pyhd8ed1ab_0
+  - aiohttp=3.9.3=py310h8d17308_1
+  - aiosignal=1.3.1=pyhd8ed1ab_0
+  - alembic=1.13.1=pyhd8ed1ab_1
+  - aniso8601=9.0.1=pyhd8ed1ab_0
+  - anyio=4.3.0=pyhd8ed1ab_0
+  - aom=3.6.0=hd77b12b_0
+  - argon2-cffi=23.1.0=pyhd8ed1ab_0
+  - argon2-cffi-bindings=21.2.0=py310h8d17308_4
+  - arrow=1.3.0=pyhd8ed1ab_0
+  - arrow-cpp=11.0.0=h2c9b28c_2
+  - asttokens=2.4.1=pyhd8ed1ab_0
+  - astunparse=1.6.3=pyhd8ed1ab_0
+  - async-lru=2.0.4=pyhd8ed1ab_0
+  - async-timeout=4.0.3=pyhd8ed1ab_0
+  - attrs=23.2.0=pyh71513ae_0
+  - aws-c-common=0.4.57=ha925a31_1
+  - aws-c-event-stream=0.1.6=h7915e17_3
+  - aws-checksums=0.1.9=hb01e4cc_0
+  - aws-sdk-cpp=1.8.185=hd77b12b_0
+  - babel=2.14.0=pyhd8ed1ab_0
+  - bcrypt=4.1.3=py310hc226416_0
+  - beautifulsoup4=4.12.3=pyha770c72_0
+  - blas=1.0=mkl
+  - bleach=6.1.0=pyhd8ed1ab_0
+  - blinker=1.7.0=pyhd8ed1ab_0
+  - blosc=1.21.5=hdccc3a2_0
+  - boost-cpp=1.84.0=h6f18f0d_2
+  - bottleneck=1.3.8=py310h3e78b6c_0
+  - brotli=1.0.9=h2bbff1b_7
+  - brotli-bin=1.0.9=h2bbff1b_7
+  - brotli-python=1.0.9=py310h00ffb61_8
+  - bzip2=1.0.8=hcfcfb64_5
+  - c-ares=1.28.1=hcfcfb64_0
+  - ca-certificates=2024.2.2=h56e8100_0
+  - cached-property=1.5.2=hd8ed1ab_1
+  - cached_property=1.5.2=pyha770c72_1
+  - cachetools=5.3.3=pyhd8ed1ab_0
+  - certifi=2024.2.2=pyhd8ed1ab_0
+  - cffi=1.16.0=py310h8d17308_0
+  - cfitsio=3.470=h2bbff1b_7
+  - charls=2.2.0=h6c2663c_0
+  - charset-normalizer=3.3.2=pyhd8ed1ab_0
+  - click=8.1.7=win_pyh7428d3b_0
+  - cloudpickle=3.0.0=pyhd8ed1ab_0
+  - colorama=0.4.6=pyhd8ed1ab_0
+  - comm=0.2.2=pyhd8ed1ab_0
+  - contourpy=1.2.1=py310h232114e_0
+  - cryptography=41.0.3=py310h3438e0d_0
+  - cycler=0.12.1=pyhd8ed1ab_0
+  - dav1d=1.2.1=hcfcfb64_0
+  - debugpy=1.8.1=py310h00ffb61_0
+  - decorator=5.1.1=pyhd8ed1ab_0
+  - defusedxml=0.7.1=pyhd8ed1ab_0
+  - docker-py=7.0.0=pyhd8ed1ab_0
+  - eigen=3.4.0=h91493d7_0
+  - entrypoints=0.4=pyhd8ed1ab_0
+  - exceptiongroup=1.2.0=pyhd8ed1ab_2
+  - executing=2.0.1=pyhd8ed1ab_0
+  - ffmpeg=4.2.3=ha925a31_0
+  - flask=3.0.3=pyhd8ed1ab_0
+  - flatbuffers=24.3.25=h63175ca_0
+  - fonttools=4.51.0=py310h8d17308_0
+  - fqdn=1.5.1=pyhd8ed1ab_0
+  - freetype=2.12.1=hdaf720e_2
+  - frozenlist=1.4.1=py310h8d17308_0
+  - gast=0.4.0=pyh9f0ad1d_0
+  - gflags=2.2.2=ha925a31_1004
+  - giflib=5.2.1=h64bf75a_3
+  - gitdb=4.0.11=pyhd8ed1ab_0
+  - gitpython=3.1.43=pyhd8ed1ab_0
+  - glib=2.80.0=h39d0aa6_3
+  - glib-tools=2.80.0=h0a98069_3
+  - glog=0.5.0=h4797de2_0
+  - google-auth=2.29.0=pyhca7485f_0
+  - google-auth-oauthlib=0.4.1=py_2
+  - google-pasta=0.2.0=pyh8c360ce_0
+  - graphene=3.3=pyhd8ed1ab_0
+  - graphql-core=3.2.3=pyhd8ed1ab_0
+  - graphql-relay=3.2.0=pyhd8ed1ab_0
+  - greenlet=3.0.3=py310h00ffb61_0
+  - grpc-cpp=1.48.2=hf108199_0
+  - grpcio=1.42.0=py310hc60d5dd_0
+  - gst-plugins-base=1.18.5=h9e645db_0
+  - gstreamer=1.18.5=hd78058f_0
+  - h11=0.14.0=pyhd8ed1ab_0
+  - h2=4.1.0=pyhd8ed1ab_0
+  - h5py=3.7.0=nompi_py310h00cbb18_100
+  - hdf5=1.12.1=nompi_h2a0e4a3_104
+  - hpack=4.0.0=pyh9f0ad1d_0
+  - httpcore=1.0.5=pyhd8ed1ab_0
+  - httpx=0.27.0=pyhd8ed1ab_0
+  - hyperframe=6.0.1=pyhd8ed1ab_0
+  - icu=58.2=ha925a31_3
+  - idna=3.6=pyhd8ed1ab_0
+  - imagecodecs=2023.1.23=py310h6c6a46e_0
+  - imageio=2.34.0=pyh4b66e23_0
+  - importlib-metadata=7.1.0=pyha770c72_0
+  - importlib_metadata=7.1.0=hd8ed1ab_0
+  - importlib_resources=6.4.0=pyhd8ed1ab_0
+  - intel-openmp=2023.1.0=h59b6b97_46320
+  - ipykernel=6.29.3=pyha63f2e9_0
+  - ipython=8.22.2=pyh7428d3b_0
+  - ipywidgets=8.1.2=pyhd8ed1ab_0
+  - isoduration=20.11.0=pyhd8ed1ab_0
+  - itsdangerous=2.2.0=pyhd8ed1ab_0
+  - jedi=0.19.1=pyhd8ed1ab_0
+  - jinja2=3.1.3=pyhd8ed1ab_0
+  - joblib=1.3.2=pyhd8ed1ab_0
+  - jpeg=9e=hcfcfb64_3
+  - json5=0.9.24=pyhd8ed1ab_0
+  - jsonpointer=2.4=py310h5588dad_3
+  - jsonschema=4.21.1=pyhd8ed1ab_0
+  - jsonschema-specifications=2023.12.1=pyhd8ed1ab_0
+  - jsonschema-with-format-nongpl=4.21.1=pyhd8ed1ab_0
+  - jupyter=1.0.0=py310haa95532_9
+  - jupyter-lsp=2.2.4=pyhd8ed1ab_0
+  - jupyter_client=8.6.1=pyhd8ed1ab_0
+  - jupyter_console=6.6.3=pyhd8ed1ab_0
+  - jupyter_core=5.7.2=py310h5588dad_0
+  - jupyter_events=0.10.0=pyhd8ed1ab_0
+  - jupyter_server=2.13.0=pyhd8ed1ab_0
+  - jupyter_server_terminals=0.5.3=pyhd8ed1ab_0
+  - jupyterlab=4.1.5=pyhd8ed1ab_0
+  - jupyterlab_pygments=0.3.0=pyhd8ed1ab_1
+  - jupyterlab_server=2.25.4=pyhd8ed1ab_0
+  - jupyterlab_widgets=3.0.10=pyhd8ed1ab_0
+  - keras=2.10.0=py310haa95532_0
+  - keras-preprocessing=1.1.2=pyhd8ed1ab_0
+  - kiwisolver=1.4.5=py310h232114e_1
+  - lazy_loader=0.4=pyhd8ed1ab_0
+  - lcms2=2.12=h83e58a3_0
+  - lerc=3.0=hd77b12b_0
+  - libabseil-static=20211102.0=cxx11_h58a5ce6_3
+  - libaec=1.1.3=h63175ca_0
+  - libavif=0.11.1=h2bbff1b_0
+  - libblas=3.9.0=20_win64_mkl
+  - libboost=1.84.0=hcc118f5_2
+  - libboost-devel=1.84.0=h91493d7_2
+  - libboost-headers=1.84.0=h57928b3_2
+  - libbrotlicommon=1.0.9=h2bbff1b_7
+  - libbrotlidec=1.0.9=h2bbff1b_7
+  - libbrotlienc=1.0.9=h2bbff1b_7
+  - libcblas=3.9.0=20_win64_mkl
+  - libclang=12.0.0=default_h627e005_2
+  - libcurl=8.5.0=h86230a5_0
+  - libdeflate=1.17=h2bbff1b_1
+  - libffi=3.4.2=h8ffe710_5
+  - libglib=2.80.0=h39d0aa6_3
+  - libiconv=1.17=hcfcfb64_2
+  - libintl=0.22.5=h5728263_2
+  - libintl-devel=0.22.5=h5728263_2
+  - liblapack=3.9.0=20_win64_mkl
+  - libogg=1.3.4=h8ffe710_1
+  - libopencv=4.6.0=haa95532_5
+  - libpng=1.6.43=h19919ed_0
+  - libprotobuf=3.20.3=h12be248_0
+  - libsodium=1.0.18=h8d14728_1
+  - libsqlite=3.45.2=hcfcfb64_0
+  - libssh2=1.10.0=hcd4344a_2
+  - libthrift=0.15.0=h636ae23_1
+  - libtiff=4.5.1=hd77b12b_0
+  - libvorbis=1.3.7=h0e60522_0
+  - libwebp=1.3.2=hcfcfb64_1
+  - libwebp-base=1.3.2=hcfcfb64_0
+  - libxml2=2.10.4=h0ad7f3c_1
+  - libxslt=1.1.37=h2bbff1b_1
+  - libzlib=1.2.13=hcfcfb64_5
+  - libzopfli=1.0.3=h0e60522_0
+  - lz4-c=1.9.4=hcfcfb64_0
+  - mako=1.3.5=pyhd8ed1ab_0
+  - markdown=3.6=pyhd8ed1ab_0
+  - markupsafe=2.1.5=py310h8d17308_0
+  - matplotlib-base=3.8.3=py310hc9baf74_0
+  - matplotlib-inline=0.1.6=pyhd8ed1ab_0
+  - mistune=3.0.2=pyhd8ed1ab_0
+  - mkl=2023.2.0=h6a75c08_50497
+  - mkl-service=2.4.1=py310h49a50da_0
+  - mkl_fft=1.3.8=py310h042f14a_1
+  - mkl_random=1.2.5=py310hd199dba_1
+  - mlflow=2.12.2=h5588dad_0
+  - mlflow-skinny=2.12.2=py310h5588dad_0
+  - mlflow-ui=2.12.2=py310h5588dad_0
+  - multidict=6.0.5=py310h8d17308_0
+  - munkres=1.1.4=pyh9f0ad1d_0
+  - nbclient=0.10.0=pyhd8ed1ab_0
+  - nbconvert=7.16.3=hd8ed1ab_0
+  - nbconvert-core=7.16.3=pyhd8ed1ab_0
+  - nbconvert-pandoc=7.16.3=hd8ed1ab_0
+  - nbformat=5.10.4=pyhd8ed1ab_0
+  - nest-asyncio=1.6.0=pyhd8ed1ab_0
+  - networkx=3.3=pyhd8ed1ab_1
+  - notebook=7.1.2=pyhd8ed1ab_0
+  - notebook-shim=0.2.4=pyhd8ed1ab_0
+  - numexpr=2.9.0=mkl_py310hc26a618_0
+  - numpy=1.24.3=py310h055cbcc_1
+  - numpy-base=1.24.3=py310h65a83cf_1
+  - oauthlib=3.2.2=pyhd8ed1ab_0
+  - opencv=4.6.0=py310ha36de5b_5
+  - openjpeg=2.4.0=h4fc8c34_0
+  - openssl=1.1.1w=hcfcfb64_0
+  - opt_einsum=3.3.0=pyhc1e730c_2
+  - orc=1.7.4=h623e30f_1
+  - overrides=7.7.0=pyhd8ed1ab_0
+  - packaging=24.0=pyhd8ed1ab_0
+  - pandas=2.2.1=py310h5da7b33_0
+  - pandoc=3.1.13=h57928b3_0
+  - pandocfilters=1.5.0=pyhd8ed1ab_0
+  - paramiko=3.4.0=pyhd8ed1ab_0
+  - parso=0.8.4=pyhd8ed1ab_0
+  - pcre2=10.43=h17e33f8_0
+  - pickleshare=0.7.5=py_1003
+  - pillow=10.2.0=py310h2bbff1b_0
+  - pip=24.0=pyhd8ed1ab_0
+  - pkgutil-resolve-name=1.3.10=pyhd8ed1ab_1
+  - platformdirs=4.2.0=pyhd8ed1ab_0
+  - ply=3.11=pyhd8ed1ab_2
+  - prometheus_client=0.20.0=pyhd8ed1ab_0
+  - prometheus_flask_exporter=0.23.0=pyhd8ed1ab_0
+  - prompt-toolkit=3.0.42=pyha770c72_0
+  - prompt_toolkit=3.0.42=hd8ed1ab_0
+  - protobuf=3.20.3=py310h5588dad_1
+  - psutil=5.9.8=py310h8d17308_0
+  - pure_eval=0.2.2=pyhd8ed1ab_0
+  - py-opencv=4.6.0=haa95532_5
+  - pyarrow=11.0.0=py310h790e06d_1
+  - pyasn1=0.5.1=pyhd8ed1ab_0
+  - pyasn1-modules=0.3.0=pyhd8ed1ab_0
+  - pycparser=2.22=pyhd8ed1ab_0
+  - pygments=2.17.2=pyhd8ed1ab_0
+  - pyjwt=2.8.0=pyhd8ed1ab_1
+  - pynacl=1.5.0=py310h635b8f1_3
+  - pyopenssl=23.2.0=pyhd8ed1ab_1
+  - pyparsing=3.1.2=pyhd8ed1ab_0
+  - pyqt=5.15.10=py310hd77b12b_0
+  - pyqt5-sip=12.13.0=py310h2bbff1b_0
+  - pysocks=1.7.1=pyh0701188_6
+  - python=3.10.13=h966fe2a_0
+  - python-dateutil=2.9.0=pyhd8ed1ab_0
+  - python-fastjsonschema=2.19.1=pyhd8ed1ab_0
+  - python-flatbuffers=24.3.25=pyh59ac667_0
+  - python-json-logger=2.0.7=pyhd8ed1ab_0
+  - python-tzdata=2024.1=pyhd8ed1ab_0
+  - python_abi=3.10=2_cp310
+  - pytz=2024.1=pyhd8ed1ab_0
+  - pyu2f=0.1.5=pyhd8ed1ab_0
+  - pywin32=306=py310h00ffb61_2
+  - pywin32-on-windows=0.1.0=pyh07e9846_2
+  - pywinpty=2.0.13=py310h00ffb61_0
+  - pyyaml=6.0.1=py310h8d17308_1
+  - pyzmq=25.1.2=py310h2849c00_0
+  - qt-main=5.15.2=he8e5bd7_7
+  - qt-webengine=5.15.9=h5bd16bc_7
+  - qtconsole=5.5.1=pyhd8ed1ab_0
+  - qtconsole-base=5.5.1=pyha770c72_0
+  - qtpy=2.4.1=pyhd8ed1ab_0
+  - qtwebkit=5.212=h2bbfb41_5
+  - querystring_parser=1.2.4=py_0
+  - re2=2022.04.01=h0e60522_0
+  - referencing=0.34.0=pyhd8ed1ab_0
+  - requests=2.31.0=pyhd8ed1ab_0
+  - requests-oauthlib=2.0.0=pyhd8ed1ab_0
+  - rfc3339-validator=0.1.4=pyhd8ed1ab_0
+  - rfc3986-validator=0.1.1=pyh9f0ad1d_0
+  - rpds-py=0.18.0=py310h87d50f1_0
+  - rsa=4.9=pyhd8ed1ab_0
+  - scikit-image=0.22.0=py310h25bd2df_0
+  - scikit-learn=1.3.0=py310h4ed8f06_1
+  - scipy=1.13.0=py310hf667824_0
+  - seaborn=0.12.2=py310haa95532_0
+  - send2trash=1.8.2=pyh08f2357_0
+  - setuptools=69.2.0=pyhd8ed1ab_0
+  - sip=6.7.12=py310h00ffb61_0
+  - six=1.16.0=pyh6c4a22f_0
+  - smmap=5.0.0=pyhd8ed1ab_0
+  - snappy=1.1.10=hfb803bf_0
+  - sniffio=1.3.1=pyhd8ed1ab_0
+  - soupsieve=2.5=pyhd8ed1ab_1
+  - sqlalchemy=2.0.30=py310ha8f682b_0
+  - sqlite=3.45.2=hcfcfb64_0
+  - sqlparse=0.5.0=pyhd8ed1ab_0
+  - stack_data=0.6.2=pyhd8ed1ab_0
+  - tbb=2021.8.0=h59b6b97_0
+  - tensorboard=2.10.0=py310haa95532_0
+  - tensorboard-data-server=0.6.1=py310haa95532_0
+  - tensorboard-plugin-wit=1.8.1=pyhd8ed1ab_0
+  - tensorflow=2.10.0=mkl_py310hd99672f_0
+  - tensorflow-base=2.10.0=mkl_py310h6a7f48e_0
+  - tensorflow-estimator=2.10.0=py310haa95532_0
+  - termcolor=2.4.0=pyhd8ed1ab_0
+  - terminado=0.18.1=pyh5737063_0
+  - threadpoolctl=3.4.0=pyhc1e730c_0
+  - tifffile=2023.2.28=pyhd8ed1ab_0
+  - tinycss2=1.2.1=pyhd8ed1ab_0
+  - tk=8.6.13=h5226925_1
+  - tomli=2.0.1=pyhd8ed1ab_0
+  - tornado=6.4=py310h8d17308_0
+  - traitlets=5.14.2=pyhd8ed1ab_0
+  - types-python-dateutil=2.9.0.20240316=pyhd8ed1ab_0
+  - typing-extensions=4.11.0=hd8ed1ab_0
+  - typing_extensions=4.11.0=pyha770c72_0
+  - typing_utils=0.1.0=pyhd8ed1ab_0
+  - tzdata=2024a=h0c530f3_0
+  - ucrt=10.0.22621.0=h57928b3_0
+  - unicodedata2=15.1.0=py310h8d17308_0
+  - uri-template=1.3.0=pyhd8ed1ab_0
+  - urllib3=2.2.1=pyhd8ed1ab_0
+  - utf8proc=2.6.1=h2bbff1b_1
+  - vc=14.3=hcf57466_18
+  - vc14_runtime=14.38.33130=h82b7239_18
+  - vs2015_runtime=14.38.33130=hcb4865c_18
+  - waitress=2.1.2=pyhd8ed1ab_0
+  - wcwidth=0.2.13=pyhd8ed1ab_0
+  - webcolors=1.13=pyhd8ed1ab_0
+  - webencodings=0.5.1=pyhd8ed1ab_2
+  - websocket-client=1.7.0=pyhd8ed1ab_0
+  - werkzeug=3.0.2=pyhd8ed1ab_0
+  - wheel=0.43.0=pyhd8ed1ab_1
+  - widgetsnbextension=4.0.10=pyhd8ed1ab_0
+  - win_inet_pton=1.1.0=pyhd8ed1ab_6
+  - winpty=0.4.3=4
+  - wrapt=1.16.0=py310h8d17308_0
+  - xz=5.4.6=h8cc25b3_0
+  - yaml=0.2.5=h8ffe710_2
+  - yarl=1.9.4=py310h8d17308_0
+  - zeromq=4.3.5=h63175ca_1
+  - zfp=1.0.1=h63175ca_0
+  - zipp=3.17.0=pyhd8ed1ab_0
+  - zlib=1.2.13=hcfcfb64_5
+  - zstd=1.5.5=h12be248_0
+prefix: C:\Users\adamw\.conda\envs\uczenie_glebokie

mlflow_project/MLproject

@@ -0,0 +1,10 @@
+name: MLflow_s464979
+
+conda_env: conda.yaml
+
+entry_points:
+  optimal_parameters:
+    parameters:
+      epochs: { type: int, default: 20 }
+      batch_size: { type: int, default: 32 }
+    command: 'python mlflow_training_model.py {epochs} {batch_size}'

mlflow_project/conda.yaml

@@ -0,0 +1,11 @@
+name: MLflow_s464979
+channels:
+  - defaults
+dependencies:
+  - python=3.10
+  - pip
+  - pip:
+      - mlflow
+      - tensorflow
+      - pandas
+      - scikit-learn

mlflow_project/mlflow_training_model.py

@@ -0,0 +1,53 @@
+import pandas as pd
+import tensorflow as tf
+import sys
+import mlflow
+from sklearn.metrics import accuracy_score
+
+mlflow.set_tracking_uri("http://localhost:5000")
+
+def main():
+    train_data = pd.read_csv('./beer_reviews_train.csv')
+    X_train = train_data[['review_aroma', 'review_appearance', 'review_palate', 'review_taste']]
+    y_train = train_data['review_overall']
+
+    tokenizer = tf.keras.preprocessing.text.Tokenizer(num_words=10000)
+    tokenizer.fit_on_texts(X_train)
+    X_train_seq = tokenizer.texts_to_sequences(X_train)
+
+    X_train_pad = tf.keras.preprocessing.sequence.pad_sequences(X_train_seq, maxlen=100)
+
+    with mlflow.start_run() as run:
+        print("MLflow run experiment_id: {0}".format(run.info.experiment_id))
+        print("MLflow run artifact_uri: {0}".format(run.info.artifact_uri))
+        model = tf.keras.Sequential([
+            tf.keras.layers.Embedding(input_dim=10000, output_dim=16, input_length=100),
+            tf.keras.layers.GlobalAveragePooling1D(),
+            tf.keras.layers.Dense(16, activation='relu'),
+            tf.keras.layers.Dense(1, activation='sigmoid')
+        ])
+
+        model.compile(optimizer='adam',
+                      loss='binary_crossentropy',
+                      metrics=['accuracy'])
+
+        print(sys.argv[1])
+        print(sys.argv[2])
+        model.fit(X_train_pad, y_train, epochs=int(sys.argv[1]), batch_size=int(sys.argv[2]), validation_split=0.1)
+
+        mlflow.log_param("epochs", int(sys.argv[1]))
+        mlflow.log_param("batch_size", int(sys.argv[2]))
+
+        test_data = pd.read_csv('./beer_reviews_test.csv')
+        X_test = test_data[['review_aroma', 'review_appearance', 'review_palate', 'review_taste']]
+        y_test = test_data['review_overall']
+
+        predictions = model.predict(X_test).flatten()
+
+        y_test_binary = (y_test >= 3).astype(int)
+
+        accuracy = accuracy_score(y_test_binary, predictions.round())
+        mlflow.log_metric("accuracy", accuracy)
+
+if __name__ == '__main__':
+    main()

mlruns/0/2824b8df5d6d414faf28b318d8b870b9/meta.yaml

@@ -0,0 +1,15 @@
+artifact_uri: file:///C:/Users/adamw/REPOS/ium_464979/mlruns/0/2824b8df5d6d414faf28b318d8b870b9/artifacts
+end_time: 1715624675138
+entry_point_name: ''
+experiment_id: '0'
+lifecycle_stage: active
+run_id: 2824b8df5d6d414faf28b318d8b870b9
+run_name: auspicious-pig-388
+run_uuid: 2824b8df5d6d414faf28b318d8b870b9
+source_name: ''
+source_type: 4
+source_version: ''
+start_time: 1715624648948
+status: 3
+tags: []
+user_id: adamw

mlruns/0/2824b8df5d6d414faf28b318d8b870b9/metrics/accuracy

@@ -0,0 +1 @@
+1715624674602 0.9242538359967604 0

mlruns/0/2824b8df5d6d414faf28b318d8b870b9/params/batch_size

@@ -0,0 +1 @@
+64

mlruns/0/2824b8df5d6d414faf28b318d8b870b9/params/epochs

@@ -0,0 +1 @@
+20

mlruns/0/2824b8df5d6d414faf28b318d8b870b9/tags/mlflow.gitRepoURL

@@ -0,0 +1 @@
+https://git.wmi.amu.edu.pl/s464979/ium_464979.git

mlruns/0/2824b8df5d6d414faf28b318d8b870b9/tags/mlflow.project.backend

@@ -0,0 +1 @@
+local

mlruns/0/2824b8df5d6d414faf28b318d8b870b9/tags/mlflow.project.entryPoint

@@ -0,0 +1 @@
+optimal_parameters

mlruns/0/2824b8df5d6d414faf28b318d8b870b9/tags/mlflow.project.env

@@ -0,0 +1 @@
+conda

mlruns/0/2824b8df5d6d414faf28b318d8b870b9/tags/mlflow.runName

@@ -0,0 +1 @@
+auspicious-pig-388

mlruns/0/2824b8df5d6d414faf28b318d8b870b9/tags/mlflow.source.git.commit

@@ -0,0 +1 @@
+0dbf6f1959cb042149cd568c8b11684f23c68024

mlruns/0/2824b8df5d6d414faf28b318d8b870b9/tags/mlflow.source.git.repoURL

@@ -0,0 +1 @@
+https://git.wmi.amu.edu.pl/s464979/ium_464979.git

mlruns/0/2824b8df5d6d414faf28b318d8b870b9/tags/mlflow.source.name

@@ -0,0 +1 @@
+file://C:\Users\adamw\REPOS\ium_464979#\mlflow_project

mlruns/0/2824b8df5d6d414faf28b318d8b870b9/tags/mlflow.source.type

@@ -0,0 +1 @@
+PROJECT

mlruns/0/2824b8df5d6d414faf28b318d8b870b9/tags/mlflow.user

@@ -0,0 +1 @@
+adamw

mlruns/0/5cbc975a93e94b8eb27d7dca17d65191/meta.yaml

@@ -0,0 +1,15 @@
+artifact_uri: file:///C:/Users/adamw/REPOS/ium_464979/mlruns/0/5cbc975a93e94b8eb27d7dca17d65191/artifacts
+end_time: 1715624631264
+entry_point_name: ''
+experiment_id: '0'
+lifecycle_stage: active
+run_id: 5cbc975a93e94b8eb27d7dca17d65191
+run_name: unruly-lamb-469
+run_uuid: 5cbc975a93e94b8eb27d7dca17d65191
+source_name: ''
+source_type: 4
+source_version: ''
+start_time: 1715624604038
+status: 3
+tags: []
+user_id: adamw

mlruns/0/5cbc975a93e94b8eb27d7dca17d65191/metrics/accuracy

@@ -0,0 +1 @@
+1715624630726 0.9242538359967604 0

mlruns/0/5cbc975a93e94b8eb27d7dca17d65191/params/batch_size

@@ -0,0 +1 @@
+32

mlruns/0/5cbc975a93e94b8eb27d7dca17d65191/params/epochs

@@ -0,0 +1 @@
+40

mlruns/0/5cbc975a93e94b8eb27d7dca17d65191/tags/mlflow.gitRepoURL

@@ -0,0 +1 @@
+https://git.wmi.amu.edu.pl/s464979/ium_464979.git

mlruns/0/5cbc975a93e94b8eb27d7dca17d65191/tags/mlflow.project.backend

@@ -0,0 +1 @@
+local

mlruns/0/5cbc975a93e94b8eb27d7dca17d65191/tags/mlflow.project.entryPoint

@@ -0,0 +1 @@
+optimal_parameters

mlruns/0/5cbc975a93e94b8eb27d7dca17d65191/tags/mlflow.project.env

@@ -0,0 +1 @@
+conda

mlruns/0/5cbc975a93e94b8eb27d7dca17d65191/tags/mlflow.runName

@@ -0,0 +1 @@
+unruly-lamb-469

mlruns/0/5cbc975a93e94b8eb27d7dca17d65191/tags/mlflow.source.git.commit

@@ -0,0 +1 @@
+0dbf6f1959cb042149cd568c8b11684f23c68024

mlruns/0/5cbc975a93e94b8eb27d7dca17d65191/tags/mlflow.source.git.repoURL

@@ -0,0 +1 @@
+https://git.wmi.amu.edu.pl/s464979/ium_464979.git

mlruns/0/5cbc975a93e94b8eb27d7dca17d65191/tags/mlflow.source.name

@@ -0,0 +1 @@
+file://C:\Users\adamw\REPOS\ium_464979#\mlflow_project

mlruns/0/5cbc975a93e94b8eb27d7dca17d65191/tags/mlflow.source.type

@@ -0,0 +1 @@
+PROJECT

mlruns/0/5cbc975a93e94b8eb27d7dca17d65191/tags/mlflow.user

@@ -0,0 +1 @@
+adamw

mlruns/0/5df6baa9d7c143d7a16314c7721ef48e/meta.yaml

@@ -0,0 +1,15 @@
+artifact_uri: file:///C:/Users/adamw/REPOS/ium_464979/mlruns/0/5df6baa9d7c143d7a16314c7721ef48e/artifacts
+end_time: 1715624529496
+entry_point_name: ''
+experiment_id: '0'
+lifecycle_stage: active
+run_id: 5df6baa9d7c143d7a16314c7721ef48e
+run_name: silent-hound-874
+run_uuid: 5df6baa9d7c143d7a16314c7721ef48e
+source_name: ''
+source_type: 4
+source_version: ''
+start_time: 1715624503432
+status: 3
+tags: []
+user_id: adamw

mlruns/0/5df6baa9d7c143d7a16314c7721ef48e/metrics/accuracy

@@ -0,0 +1 @@
+1715624528800 0.9242538359967604 0

mlruns/0/5df6baa9d7c143d7a16314c7721ef48e/params/batch_size

@@ -0,0 +1 @@
+32

mlruns/0/5df6baa9d7c143d7a16314c7721ef48e/params/epochs

@@ -0,0 +1 @@
+20

mlruns/0/5df6baa9d7c143d7a16314c7721ef48e/tags/mlflow.gitRepoURL

@@ -0,0 +1 @@
+https://git.wmi.amu.edu.pl/s464979/ium_464979.git

mlruns/0/5df6baa9d7c143d7a16314c7721ef48e/tags/mlflow.project.backend

@@ -0,0 +1 @@
+local

mlruns/0/5df6baa9d7c143d7a16314c7721ef48e/tags/mlflow.project.entryPoint

@@ -0,0 +1 @@
+optimal_parameters

mlruns/0/5df6baa9d7c143d7a16314c7721ef48e/tags/mlflow.project.env

@@ -0,0 +1 @@
+conda

mlruns/0/5df6baa9d7c143d7a16314c7721ef48e/tags/mlflow.runName

@@ -0,0 +1 @@
+silent-hound-874

mlruns/0/5df6baa9d7c143d7a16314c7721ef48e/tags/mlflow.source.git.commit

@@ -0,0 +1 @@
+0dbf6f1959cb042149cd568c8b11684f23c68024

mlruns/0/5df6baa9d7c143d7a16314c7721ef48e/tags/mlflow.source.git.repoURL

@@ -0,0 +1 @@
+https://git.wmi.amu.edu.pl/s464979/ium_464979.git

mlruns/0/5df6baa9d7c143d7a16314c7721ef48e/tags/mlflow.source.name

@@ -0,0 +1 @@
+file://C:\Users\adamw\REPOS\ium_464979#\mlflow_project

mlruns/0/5df6baa9d7c143d7a16314c7721ef48e/tags/mlflow.source.type

@@ -0,0 +1 @@
+PROJECT

mlruns/0/5df6baa9d7c143d7a16314c7721ef48e/tags/mlflow.user

@@ -0,0 +1 @@
+adamw

mlruns/0/meta.yaml

@@ -0,0 +1,6 @@
+artifact_location: file:///C:/Users/adamw/REPOS/ium_464979/mlruns/0
+creation_time: 1715624503432
+experiment_id: '0'
+last_update_time: 1715624503432
+lifecycle_stage: active
+name: Default

sacred/sacred_runs/1/config.json

@@ -0,0 +1,5 @@
+{
+  "batch_size": 32,
+  "epochs": 10,
+  "seed": 373303958
+}

sacred/sacred_runs/1/metrics.json

@@ -0,0 +1 @@
+{}

sacred/sacred_runs/1/run.json

@@ -0,0 +1,100 @@
+{
+  "artifacts": [
+    "beer_review_model.h5"
+  ],
+  "command": "run_experiment",
+  "experiment": {
+    "base_dir": "C:\\Users\\adamw\\REPOS\\ium_464979\\sacred",
+    "dependencies": [
+      "keras==2.12.0",
+      "numpy==1.23.5",
+      "sacred==0.8.5",
+      "scikit-learn==1.2.2"
+    ],
+    "mainfile": "sacred_training_model.py",
+    "name": "464979",
+    "repositories": [
+      {
+        "commit": "e9f53be95453a8da8811653ba3c4a6e75895cd33",
+        "dirty": true,
+        "url": "https://git.wmi.amu.edu.pl/s464979/ium_464979.git"
+      }
+    ],
+    "sources": [
+      [
+        "sacred_training_model.py",
+        "_sources\\sacred_training_model_2a1e89d7c820c7a00319e1e22827c7f9.py"
+      ]
+    ]
+  },
+  "heartbeat": "2024-06-11T17:21:14.840246",
+  "host": {
+    "ENV": {},
+    "cpu": "Intel(R) Core(TM) i7-9750H CPU @ 2.60GHz",
+    "gpus": {
+      "driver_version": "555.85",
+      "gpus": [
+        {
+          "model": "NVIDIA GeForce GTX 1660 Ti",
+          "persistence_mode": false,
+          "total_memory": 6144
+        }
+      ]
+    },
+    "hostname": "DESKTOP-9SEHQM2",
+    "os": [
+      "Windows",
+      "Windows-10-10.0.19045-SP0"
+    ],
+    "python_version": "3.11.7"
+  },
+  "meta": {
+    "command": "run_experiment",
+    "config_updates": {},
+    "named_configs": [],
+    "options": {
+      "--beat-interval": null,
+      "--capture": null,
+      "--comment": null,
+      "--debug": false,
+      "--enforce_clean": false,
+      "--file_storage": null,
+      "--force": false,
+      "--help": false,
+      "--id": null,
+      "--loglevel": null,
+      "--mongo_db": null,
+      "--name": null,
+      "--pdb": false,
+      "--print-config": false,
+      "--priority": null,
+      "--queue": false,
+      "--s3": null,
+      "--sql": null,
+      "--tiny_db": null,
+      "--unobserved": false,
+      "COMMAND": null,
+      "UPDATE": [],
+      "help": false,
+      "with": false
+    }
+  },
+  "resources": [
+    [
+      "C:\\Users\\adamw\\REPOS\\ium_464979\\sacred\\beer_reviews_train.csv",
+      "sacred_runs\\_resources\\beer_reviews_train_e8dab75a0ec202f56510a0e1f9926ad7.csv"
+    ],
+    [
+      "C:\\Users\\adamw\\REPOS\\ium_464979\\sacred\\beer_reviews_test.csv",
+      "sacred_runs\\_resources\\beer_reviews_test_56070f83bef3ee1d17d1a632aa55b798.csv"
+    ]
+  ],
+  "result": {
+    "dtype": "float64",
+    "py/object": "numpy.float64",
+    "value": 0.9237146778770103
+  },
+  "start_time": "2024-06-11T17:21:03.851734",
+  "status": "COMPLETED",
+  "stop_time": "2024-06-11T17:21:14.839247"
+}

sacred/sacred_runs/2/config.json

@@ -0,0 +1,5 @@
+{
+  "batch_size": 32,
+  "epochs": 10,
+  "seed": 541882551
+}

sacred/sacred_runs/2/metrics.json

@@ -0,0 +1 @@
+{}

sacred/sacred_runs/2/run.json

@@ -0,0 +1,100 @@
+{
+  "artifacts": [
+    "beer_review_sentiment_model.keras"
+  ],
+  "command": "run_experiment",
+  "experiment": {
+    "base_dir": "C:\\Users\\adamw\\REPOS\\ium_464979\\sacred",
+    "dependencies": [
+      "keras==2.12.0",
+      "numpy==1.23.5",
+      "sacred==0.8.5",
+      "scikit-learn==1.2.2"
+    ],
+    "mainfile": "sacred_training_model.py",
+    "name": "464979",
+    "repositories": [
+      {
+        "commit": "490b8cf77306ea482543e03ba29e37b07f689ae1",
+        "dirty": true,
+        "url": "https://git.wmi.amu.edu.pl/s464979/ium_464979.git"
+      }
+    ],
+    "sources": [
+      [
+        "sacred_training_model.py",
+        "_sources\\sacred_training_model_ccb7ce6317e0e291ec9a10a9f4fffffe.py"
+      ]
+    ]
+  },
+  "heartbeat": "2024-06-11T21:08:46.548013",
+  "host": {
+    "ENV": {},
+    "cpu": "Intel(R) Core(TM) i7-9750H CPU @ 2.60GHz",
+    "gpus": {
+      "driver_version": "555.85",
+      "gpus": [
+        {
+          "model": "NVIDIA GeForce GTX 1660 Ti",
+          "persistence_mode": false,
+          "total_memory": 6144
+        }
+      ]
+    },
+    "hostname": "DESKTOP-9SEHQM2",
+    "os": [
+      "Windows",
+      "Windows-10-10.0.19045-SP0"
+    ],
+    "python_version": "3.11.7"
+  },
+  "meta": {
+    "command": "run_experiment",
+    "config_updates": {},
+    "named_configs": [],
+    "options": {
+      "--beat-interval": null,
+      "--capture": null,
+      "--comment": null,
+      "--debug": false,
+      "--enforce_clean": false,
+      "--file_storage": null,
+      "--force": false,
+      "--help": false,
+      "--id": null,
+      "--loglevel": null,
+      "--mongo_db": null,
+      "--name": null,
+      "--pdb": false,
+      "--print-config": false,
+      "--priority": null,
+      "--queue": false,
+      "--s3": null,
+      "--sql": null,
+      "--tiny_db": null,
+      "--unobserved": false,
+      "COMMAND": null,
+      "UPDATE": [],
+      "help": false,
+      "with": false
+    }
+  },
+  "resources": [
+    [
+      "C:\\Users\\adamw\\REPOS\\ium_464979\\sacred\\beer_reviews_train.csv",
+      "sacred_runs\\_resources\\beer_reviews_train_e8dab75a0ec202f56510a0e1f9926ad7.csv"
+    ],
+    [
+      "C:\\Users\\adamw\\REPOS\\ium_464979\\sacred\\beer_reviews_test.csv",
+      "sacred_runs\\_resources\\beer_reviews_test_56070f83bef3ee1d17d1a632aa55b798.csv"
+    ]
+  ],
+  "result": {
+    "dtype": "float64",
+    "py/object": "numpy.float64",
+    "value": 0.9237146778770103
+  },
+  "start_time": "2024-06-11T21:08:35.823687",
+  "status": "COMPLETED",
+  "stop_time": "2024-06-11T21:08:46.547012"
+}

sacred/sacred_runs/_sources/sacred_training_model_2a1e89d7c820c7a00319e1e22827c7f9.py

@@ -0,0 +1,85 @@
+import pandas as pd
+from tensorflow.keras.preprocessing.text import Tokenizer
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Embedding, GlobalAveragePooling1D, Dense
+from tensorflow.keras.models import load_model
+from sklearn.metrics import accuracy_score, precision_recall_fscore_support, mean_squared_error
+from sacred import Experiment
+from sacred.observers import MongoObserver, FileStorageObserver
+from math import sqrt
+
+ex = Experiment('464979')
+# ex.observers.append(MongoObserver(url='mongodb://admin:IUM_2021@tzietkiewicz.vm.wmi.amu.edu.pl:27017'))
+ex.observers.append(FileStorageObserver('sacred_runs'))
+
+@ex.config
+def my_config():
+    epochs = 10
+    batch_size = 32
+
+@ex.automain
+def run_experiment(epochs, batch_size, _run):
+    train_data = pd.read_csv('beer_reviews_train.csv')
+    X_train = train_data[['review_aroma', 'review_appearance', 'review_palate', 'review_taste']]
+    y_train = train_data['review_overall']
+
+    tokenizer = Tokenizer(num_words=10000)
+    tokenizer.fit_on_texts(X_train)
+    X_train_seq = tokenizer.texts_to_sequences(X_train)
+
+    X_train_pad = pad_sequences(X_train_seq, maxlen=100)
+
+    model = Sequential([
+        Embedding(input_dim=10000, output_dim=16, input_length=100),
+        GlobalAveragePooling1D(),
+        Dense(16, activation='relu'),
+        Dense(1, activation='sigmoid')
+    ])
+
+    model.compile(optimizer='adam',
+                  loss='binary_crossentropy',
+                  metrics=['accuracy'])
+
+    model.fit(X_train_pad, y_train, epochs=epochs, batch_size=batch_size, validation_split=0.1)
+
+    model.save('beer_review_sentiment_model.keras')
+    _run.add_artifact('beer_review_model.h5')
+
+    test_data = pd.read_csv('beer_reviews_test.csv')
+    X_test = test_data[['review_aroma', 'review_appearance', 'review_palate', 'review_taste']]
+    y_test = test_data['review_overall']
+
+    tokenizer = Tokenizer(num_words=10000)
+    tokenizer.fit_on_texts(X_test)
+
+    X_test_text = X_test.astype(str).agg(' '.join, axis=1)
+    X_test_seq = tokenizer.texts_to_sequences(X_test_text)
+    X_test_pad = pad_sequences(X_test_seq, maxlen=100)
+
+    predictions = model.predict(X_test_pad)
+
+    if len(predictions.shape) > 1:
+        predictions = predictions[:, 0]
+
+    results = pd.DataFrame({'Predictions': predictions, 'Actual': y_test})
+    results.to_csv('beer_review_sentiment_predictions.csv', index=False)
+
+    y_pred = results['Predictions']
+    y_test = results['Actual']
+    y_test_binary = (y_test >= 3).astype(int)
+
+    accuracy = accuracy_score(y_test_binary, y_pred.round())
+    precision, recall, f1, _ = precision_recall_fscore_support(y_test_binary, y_pred.round(), average='micro')
+    rmse = sqrt(mean_squared_error(y_test, y_pred))
+
+    print(f'Accuracy: {accuracy}')
+    print(f'Micro-avg Precision: {precision}')
+    print(f'Micro-avg Recall: {recall}')
+    print(f'F1 Score: {f1}')
+    print(f'RMSE: {rmse}')
+
+    _run.add_resource('./beer_reviews_train.csv')
+    _run.add_resource('./beer_reviews_test.csv')
+
+    return accuracy

sacred/sacred_runs/_sources/sacred_training_model_ccb7ce6317e0e291ec9a10a9f4fffffe.py

@@ -0,0 +1,84 @@
+import pandas as pd
+from tensorflow.keras.preprocessing.text import Tokenizer
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Embedding, GlobalAveragePooling1D, Dense
+from sklearn.metrics import accuracy_score, precision_recall_fscore_support, mean_squared_error
+from sacred import Experiment
+from sacred.observers import MongoObserver, FileStorageObserver
+from math import sqrt
+
+ex = Experiment('464979')
+# ex.observers.append(MongoObserver(url='mongodb://admin:IUM_2021@tzietkiewicz.vm.wmi.amu.edu.pl:27017'))
+ex.observers.append(FileStorageObserver('sacred_runs'))
+
+@ex.config
+def my_config():
+    epochs = 10
+    batch_size = 32
+
+@ex.automain
+def run_experiment(epochs, batch_size, _run):
+    train_data = pd.read_csv('beer_reviews_train.csv')
+    X_train = train_data[['review_aroma', 'review_appearance', 'review_palate', 'review_taste']]
+    y_train = train_data['review_overall']
+
+    tokenizer = Tokenizer(num_words=10000)
+    tokenizer.fit_on_texts(X_train)
+    X_train_seq = tokenizer.texts_to_sequences(X_train)
+
+    X_train_pad = pad_sequences(X_train_seq, maxlen=100)
+
+    model = Sequential([
+        Embedding(input_dim=10000, output_dim=16, input_length=100),
+        GlobalAveragePooling1D(),
+        Dense(16, activation='relu'),
+        Dense(1, activation='sigmoid')
+    ])
+
+    model.compile(optimizer='adam',
+                  loss='binary_crossentropy',
+                  metrics=['accuracy'])
+
+    model.fit(X_train_pad, y_train, epochs=epochs, batch_size=batch_size, validation_split=0.1)
+
+    model.save('beer_review_sentiment_model.keras')
+    _run.add_artifact('beer_review_sentiment_model.keras')
+
+    test_data = pd.read_csv('beer_reviews_test.csv')
+    X_test = test_data[['review_aroma', 'review_appearance', 'review_palate', 'review_taste']]
+    y_test = test_data['review_overall']
+
+    tokenizer = Tokenizer(num_words=10000)
+    tokenizer.fit_on_texts(X_test)
+
+    X_test_text = X_test.astype(str).agg(' '.join, axis=1)
+    X_test_seq = tokenizer.texts_to_sequences(X_test_text)
+    X_test_pad = pad_sequences(X_test_seq, maxlen=100)
+
+    predictions = model.predict(X_test_pad)
+
+    if len(predictions.shape) > 1:
+        predictions = predictions[:, 0]
+
+    results = pd.DataFrame({'Predictions': predictions, 'Actual': y_test})
+    results.to_csv('beer_review_sentiment_predictions.csv', index=False)
+
+    y_pred = results['Predictions']
+    y_test = results['Actual']
+    y_test_binary = (y_test >= 3).astype(int)
+
+    accuracy = accuracy_score(y_test_binary, y_pred.round())
+    precision, recall, f1, _ = precision_recall_fscore_support(y_test_binary, y_pred.round(), average='micro')
+    rmse = sqrt(mean_squared_error(y_test, y_pred))
+
+    print(f'Accuracy: {accuracy}')
+    print(f'Micro-avg Precision: {precision}')
+    print(f'Micro-avg Recall: {recall}')
+    print(f'F1 Score: {f1}')
+    print(f'RMSE: {rmse}')
+
+    _run.add_resource('./beer_reviews_train.csv')
+    _run.add_resource('./beer_reviews_test.csv')
+
+    return accuracy

sacred/sacred_training_model.py

@@ -0,0 +1,84 @@
+import pandas as pd
+from tensorflow.keras.preprocessing.text import Tokenizer
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Embedding, GlobalAveragePooling1D, Dense
+from sklearn.metrics import accuracy_score, precision_recall_fscore_support, mean_squared_error
+from sacred import Experiment
+from sacred.observers import MongoObserver, FileStorageObserver
+from math import sqrt
+
+ex = Experiment('464979')
+ex.observers.append(MongoObserver(url='mongodb://admin:IUM_2021@tzietkiewicz.vm.wmi.amu.edu.pl:27017'))
+ex.observers.append(FileStorageObserver('sacred_runs'))
+
+@ex.config
+def my_config():
+    epochs = 10
+    batch_size = 32
+
+@ex.automain
+def run_experiment(epochs, batch_size, _run):
+    train_data = pd.read_csv('beer_reviews_train.csv')
+    X_train = train_data[['review_aroma', 'review_appearance', 'review_palate', 'review_taste']]
+    y_train = train_data['review_overall']
+
+    tokenizer = Tokenizer(num_words=10000)
+    tokenizer.fit_on_texts(X_train)
+    X_train_seq = tokenizer.texts_to_sequences(X_train)
+
+    X_train_pad = pad_sequences(X_train_seq, maxlen=100)
+
+    model = Sequential([
+        Embedding(input_dim=10000, output_dim=16, input_length=100),
+        GlobalAveragePooling1D(),
+        Dense(16, activation='relu'),
+        Dense(1, activation='sigmoid')
+    ])
+
+    model.compile(optimizer='adam',
+                  loss='binary_crossentropy',
+                  metrics=['accuracy'])
+
+    model.fit(X_train_pad, y_train, epochs=epochs, batch_size=batch_size, validation_split=0.1)
+
+    model.save('beer_review_sentiment_model.keras')
+    _run.add_artifact('beer_review_sentiment_model.keras')
+
+    test_data = pd.read_csv('beer_reviews_test.csv')
+    X_test = test_data[['review_aroma', 'review_appearance', 'review_palate', 'review_taste']]
+    y_test = test_data['review_overall']
+
+    tokenizer = Tokenizer(num_words=10000)
+    tokenizer.fit_on_texts(X_test)
+
+    X_test_text = X_test.astype(str).agg(' '.join, axis=1)
+    X_test_seq = tokenizer.texts_to_sequences(X_test_text)
+    X_test_pad = pad_sequences(X_test_seq, maxlen=100)
+
+    predictions = model.predict(X_test_pad)
+
+    if len(predictions.shape) > 1:
+        predictions = predictions[:, 0]
+
+    results = pd.DataFrame({'Predictions': predictions, 'Actual': y_test})
+    results.to_csv('beer_review_sentiment_predictions.csv', index=False)
+
+    y_pred = results['Predictions']
+    y_test = results['Actual']
+    y_test_binary = (y_test >= 3).astype(int)
+
+    accuracy = accuracy_score(y_test_binary, y_pred.round())
+    precision, recall, f1, _ = precision_recall_fscore_support(y_test_binary, y_pred.round(), average='micro')
+    rmse = sqrt(mean_squared_error(y_test, y_pred))
+
+    print(f'Accuracy: {accuracy}')
+    print(f'Micro-avg Precision: {precision}')
+    print(f'Micro-avg Recall: {recall}')
+    print(f'F1 Score: {f1}')
+    print(f'RMSE: {rmse}')
+
+    _run.add_resource('./beer_reviews_train.csv')
+    _run.add_resource('./beer_reviews_test.csv')
+
+    return accuracy