Further dataset updates for the new URLs.

crate · Jan 10, 2025 · 0447079 · 0447079
1 parent 5e8e24d
commit 0447079
Show file tree

Hide file tree

Showing 3 changed files with 14 additions and 14 deletions.
diff --git a/topic/machine-learning/automl/test.py b/topic/machine-learning/automl/test.py
@@ -53,7 +53,7 @@ def churn_dataset(cratedb):
     Provide test case with a provisioned dataset.
     """
     cratedb.import_csv_pandas(
-        filepath="https://github.com/crate/cratedb-datasets/raw/main/machine-learning/automl/churn-dataset.csv",
+        filepath="https://cdn.crate.io/downloads/datasets/cratedb-datasets/machine-learning/automl/churn-dataset.csv",
         tablename="pycaret_churn",
     )
     cratedb.run_sql("REFRESH TABLE pycaret_churn;")

diff --git a/topic/machine-learning/llm-langchain/cratedb-vectorstore-rag-openai-sql.ipynb b/topic/machine-learning/llm-langchain/cratedb-vectorstore-rag-openai-sql.ipynb
@@ -196,7 +196,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "loader = PyPDFLoader(\"https://github.com/crate/cratedb-datasets/raw/main/machine-learning/fulltext/White%20paper%20-%20Time-series%20data%20in%20manufacturing.pdf\")\n",
+    "loader = PyPDFLoader(\"https://cdn.crate.io/downloads/datasets/cratedb-datasets/machine-learning/fulltext/White%20paper%20-%20Time-series%20data%20in%20manufacturing.pdf\")\n",
     "text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)\n",
     "pages = loader.load_and_split(text_splitter)"
    ]

diff --git a/topic/machine-learning/mlops-mlflow/tracking_merlion.ipynb b/topic/machine-learning/mlops-mlflow/tracking_merlion.ipynb
@@ -32,7 +32,7 @@
     "\n",
     "\n",
     "# Download the data from the Numenta Anomaly Benchmark\n",
-    "data = pd.read_csv(\"https://github.com/crate/cratedb-datasets/raw/main/timeseries/nab-machine-failure.csv\")\n",
+    "data = pd.read_csv(\"https://cdn.crate.io/downloads/datasets/cratedb-datasets/timeseries/nab-machine-failure.csv\")\n",
     "\n",
     "# Connect to a self-managed CrateDB instance.\n",
     "CRATEDB_HTTP_URL_DEFAULT = \"http://crate@localhost:4200/\"\n",
@@ -47,16 +47,22 @@
   },
   {
    "cell_type": "markdown",
-   "source": [
-    "2. Import data into CrateDB"
-   ],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "source": [
+    "2. Import data into CrateDB"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "is_executing": true
+    }
+   },
    "outputs": [],
    "source": [
     "# Split the data into chunks of 1000 rows each for better insert performance\n",
@@ -72,13 +78,7 @@
     "    for chunk in chunks:\n",
     "        cursor.executemany(\"INSERT INTO machine_data (timestamp, temperature) VALUES (?, ?);\", list(chunk.itertuples(index=False, name=None)))\n",
     "    cursor.execute(\"REFRESH TABLE machine_data;\")"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "is_executing": true
-    }
-   }
+   ]
   },
   {
    "cell_type": "markdown",