Upgrade Base Image: colab_20250404-060113_RC00

Dockerfile.tmpl

@@ -7,6 +7,10 @@ FROM gcr.io/kaggle-images/python-lightgbm-whl:${BASE_IMAGE_TAG}-${LIGHTGBM_VERSI
 {{ end }}
 FROM ${BASE_IMAGE}:${BASE_IMAGE_TAG}
 
+#b/415358342: UV reports missing requirements files https://github.com/googlecolab/colabtools/issues/5237
+ENV UV_CONSTRAINT= \ 
+    UV_BUILD_CONSTRAINT=
+
 ADD kaggle_requirements.txt /kaggle_requirements.txt
 
 # Freeze existing requirements from base image for critical packages:
@@ -27,26 +31,19 @@ RUN uv pip install --system -r /requirements.txt
 RUN uv pip uninstall --system google-cloud-bigquery-storage
 
 # b/394382016: sigstore (dependency of kagglehub) requires a prerelease packages, installing separate.
-RUN uv pip install --system --force-reinstall --prerelease=allow kagglehub[pandas-datasets,hf-datasets,signing]>=0.3.9
-
-# b/408284143: google-cloud-automl 2.0.0 introduced incompatible API changes, need to pin to 1.0.1
-
-# b/408284435: Keras 3.6 broke test_keras.py > test_train > keras.datasets.mnist.load_data()
-# See https://github.com/keras-team/keras/commit/dcefb139863505d166dd1325066f329b3033d45a
-# Colab base is on Keras 3.8, we have to install the package separately
-RUN uv pip install --system google-cloud-automl==1.0.1 google-cloud-aiplatform google-cloud-translate==3.12.1 \
-    google-cloud-videointelligence google-cloud-vision google-genai "keras<3.6"
+# b/408284143: google-cloud-automl 2.0.0 introduced incompatible API changes, need to pin to 1.0.1,
+# installed outside of kaggle_requirements.txt due to requiring an incompatibile version of protobuf.
+RUN uv pip install --system --force-reinstall --prerelease=allow kagglehub[pandas-datasets,hf-datasets,signing]>=0.3.12 \
+    google-cloud-automl==1.0.1
 
 # uv cannot install this in requirements.txt without --no-build-isolation
 # to avoid affecting the larger build, we'll post-install it.
 RUN uv pip install --no-build-isolation --system "git+https://github.com/Kaggle/learntools"
 
 # b/408281617: Torch is adamant that it can not install cudnn 9.3.x, only 9.1.x, but Tensorflow can only support 9.3.x.
 # This conflict causes a number of package downgrades, which are handled in this command
-# b/302136621: Fix eli5 import for learntools
 RUN uv pip install --system --force-reinstall --extra-index-url https://pypi.nvidia.com "cuml-cu12==25.2.1" \
-    "nvidia-cudnn-cu12==9.3.0.75" scipy tsfresh scikit-learn==1.2.2 category-encoders eli5
-
+    "nvidia-cudnn-cu12==9.3.0.75"
 RUN uv pip install --system --force-reinstall "pynvjitlink-cu12==0.5.2"
 
 # b/385145217 Latest Colab lacks mkl numpy, install it.
@@ -56,10 +53,10 @@ RUN uv pip install --system --force-reinstall -i https://pypi.anaconda.org/intel
 RUN uv pip install --system "tbb>=2022" "libpysal==4.9.2"
 
 # b/404590350: Ray and torchtune have conflicting tune cli, we will prioritize torchtune.
-RUN uv pip install --system --force-reinstall --no-deps torchtune
+# b/415358158: Gensim removed from Colab image to upgrade scipy
+RUN uv pip install --system --force-reinstall --no-deps torchtune gensim
 
 # Adding non-package dependencies:
-
 ADD clean-layer.sh  /tmp/clean-layer.sh
 ADD patches/nbconvert-extensions.tpl /opt/kaggle/nbconvert-extensions.tpl
 ADD patches/template_conf.json /opt/kaggle/conf.json
@@ -171,13 +168,13 @@ RUN mkdir -p /root/.jupyter && touch /root/.jupyter/jupyter_nbconvert_config.py
     mkdir -p /etc/ipython/ && echo "c = get_config(); c.IPKernelApp.matplotlib = 'inline'" > /etc/ipython/ipython_config.py && \
     /tmp/clean-layer.sh
 
-# Fix to import bq_helper library without downgrading setuptools
+# Fix to import bq_helper library without downgrading setuptools and upgrading protobuf
 RUN mkdir -p ~/src && git clone https://github.com/SohierDane/BigQuery_Helper ~/src/BigQuery_Helper && \
     mkdir -p ~/src/BigQuery_Helper/bq_helper && \
     mv ~/src/BigQuery_Helper/bq_helper.py ~/src/BigQuery_Helper/bq_helper/__init__.py && \
     mv ~/src/BigQuery_Helper/test_helper.py ~/src/BigQuery_Helper/bq_helper/ && \
     sed -i 's/)/packages=["bq_helper"])/g' ~/src/BigQuery_Helper/setup.py && \
-    uv pip install --system -e ~/src/BigQuery_Helper && \
+    uv pip install --system -e ~/src/BigQuery_Helper "protobuf<3.21"&& \
     /tmp/clean-layer.sh
 
 

config.txt

@@ -1,5 +1,5 @@
 BASE_IMAGE=us-docker.pkg.dev/colab-images/public/runtime
-BASE_IMAGE_TAG=release-colab_20250219-060225_RC01
+BASE_IMAGE_TAG=release-colab_20250404-060113_RC00
 LIGHTGBM_VERSION=4.6.0
 CUDA_MAJOR_VERSION=12
 CUDA_MINOR_VERSION=5

kaggle_requirements.txt

@@ -20,18 +20,20 @@ arrow
 bayesian-optimization
 boto3
 catboost
+category-encoders
 cesium
 comm
 cytoolz
 dask-expr
 # Older versions of datasets fail with "Loading a dataset cached in a LocalFileSystem is not supported"
 # https://stackoverflow.com/questions/77433096/notimplementederror-loading-a-dataset-cached-in-a-localfilesystem-is-not-suppor
 datasets>=2.14.6
-datashader
 deap
 dipy
 docker
 easyocr
+# b/302136621: Fix eli5 import for learntools
+eli5
 emoji
 fastcore>=1.7.20
 fasttext
@@ -42,6 +44,13 @@ fuzzywuzzy
 geojson
 # geopandas > v0.14.4 breaks learn tools
 geopandas==v0.14.4
+gensim
+google-cloud-aiplatform
+# b/315753846: Unpin translate package.
+google-cloud-translate==3.12.1
+google-cloud-videointelligence
+google-cloud-vision
+google-genai
 gpxpy
 h2o
 haversine
@@ -112,12 +121,15 @@ qtconsole
 ray
 rgf-python
 s3fs
+scikit-learn==1.2.2
 # Scikit-learn accelerated library for x86
 scikit-learn-intelex>=2023.0.1
 scikit-multilearn
 scikit-optimize
 scikit-plot
 scikit-surprise
+# b/415358158: Gensim removed from Colab image to upgrade scipy to 1.14.1
+scipy==1.15.1
 # Also pinning seaborn for learntools
 seaborn==0.12.2
 git+https://github.com/facebookresearch/segment-anything.git

tests/test_automl.py

@@ -8,7 +8,9 @@
 
 def _make_credentials():
     import google.auth.credentials
-    return Mock(spec=google.auth.credentials.Credentials)
+    credentials = Mock(spec=google.auth.credentials.Credentials)
+    credentials.universe_domain = 'googleapis.com'
+    return credentials
 
 class TestAutoMl(unittest.TestCase):
 

tests/test_gcs.py

@@ -8,7 +8,9 @@
 
 def _make_credentials():
     import google.auth.credentials
-    return Mock(spec=google.auth.credentials.Credentials)
+    credentials = Mock(spec=google.auth.credentials.Credentials)
+    credentials.universe_domain = 'googleapis.com'
+    return credentials
 
 class TestStorage(unittest.TestCase):
 

tests/test_keras.py

@@ -9,10 +9,11 @@
 
 class TestKeras(unittest.TestCase):
     def test_train(self):
-        # Load the data and split it between train and test sets
-        (x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data(
-            path='/input/tests/data/mnist.npz'
-        )
+        path = '/input/tests/data/mnist.npz'
+        with np.load(path) as f:
+            x_train, y_train = f['x_train'], f['y_train']
+            x_test, y_test = f['x_test'], f['y_test']
+
 
         # Scale images to the [0, 1] range
         x_train = x_train.astype("float32") / 255