Added section on case sensitivity to Cassandra notebook

khliland · Oct 7, 2024 · 42a84b8 · 42a84b8
1 parent 5486f46
commit 42a84b8
Show file tree

Hide file tree

Showing 198 changed files with 5,338 additions and 1,667,211 deletions.
diff --git a/D2Dbook/3_Data_sources/2_Databases/2_MySQL.ipynb b/D2Dbook/3_Data_sources/2_Databases/2_MySQL.ipynb
@@ -32,7 +32,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 8,
    "metadata": {
     "slideshow": {
      "slide_type": "slide"
@@ -203,12 +203,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
     },
-    "tags": []
+    "tags": [
+     "raises-exception"
+    ]
    },
    "outputs": [],
    "source": [
@@ -220,7 +222,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 13,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -248,7 +250,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 14,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -276,7 +278,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 15,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -291,7 +293,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 16,
    "metadata": {
     "slideshow": {
      "slide_type": "fragment"
@@ -339,7 +341,7 @@
  "metadata": {
   "celltoolbar": "Slideshow",
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "IND320_2024",
    "language": "python",
    "name": "python3"
   },

diff --git a/D2Dbook/3_Data_sources/2_Databases/3_Cassandra.ipynb b/D2Dbook/3_Data_sources/2_Databases/3_Cassandra.ipynb
@@ -72,7 +72,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2024-08-17T10:25:34.787878Z",
@@ -190,6 +190,116 @@
     "session.execute(\"INSERT INTO my_first_table (ind, company, model) VALUES (3, 'Polestar', '3');\")"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Query the data\n",
+    "rows = session.execute(\"SELECT * FROM my_first_table;\")\n",
+    "for i in rows:\n",
+    "    print(i)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "slideshow": {
+     "slide_type": "slide"
+    },
+    "tags": []
+   },
+   "source": [
+    "### Case sensitivity\n",
+    "- Cassandra is by default case insensitive in column names.\n",
+    "- To use column names with capital letters, use double quotation marks both when creating tables and when inserting data.\n",
+    "- The effect of insensitivity may be surprising.\n",
+    "    - Look carefully at the use of quotation marks and error message below."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "slideshow": {
+     "slide_type": "slide"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "session.set_keyspace('my_first_keyspace')\n",
+    "session.execute(\"DROP TABLE IF EXISTS my_first_keyspace.case_insensitive;\") # Starting from scratch every time\n",
+    "session.execute(\"CREATE TABLE IF NOT EXISTS case_insensitive (Capital int PRIMARY KEY, Letters text, Everywhere text);\")\n",
+    "session.execute(\"DROP TABLE IF EXISTS my_first_keyspace.case_sensitive;\") # Starting from scratch every time\n",
+    "session.execute(\"CREATE TABLE IF NOT EXISTS case_sensitive (\\\"Capital\\\" int PRIMARY KEY, \\\"Letters\\\" text, \\\"Everywhere\\\" text);\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "slideshow": {
+     "slide_type": "fragment"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "session.execute(\"INSERT INTO case_insensitive (Capital, Letters, Everywhere) VALUES (1, 'Tesla', 'Model S');\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "slideshow": {
+     "slide_type": "fragment"
+    },
+    "tags": [
+     "raises-exception"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "session.execute(\"INSERT INTO case_sensitive (Capital, Letters, Everywhere) VALUES (1, 'Tesla', 'Model S');\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "slideshow": {
+     "slide_type": "fragment"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "session.execute(\"INSERT INTO case_sensitive (\\\"Capital\\\", \\\"Letters\\\", \\\"Everywhere\\\") VALUES (1, 'Tesla', 'Model S');\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "slideshow": {
+     "slide_type": "slide"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# Query the data\n",
+    "rows = session.execute(\"SELECT * FROM case_insensitive;\")\n",
+    "for i in rows:\n",
+    "    print(i)\n",
+    "rows = session.execute(\"SELECT * FROM case_sensitive;\")\n",
+    "for i in rows:\n",
+    "    print(i)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {

diff --git a/D2Dbook/3_Data_sources/2_Databases/4_Spark.ipynb b/D2Dbook/3_Data_sources/2_Databases/4_Spark.ipynb
@@ -93,7 +93,8 @@
     "    config('spark.sql.extensions', 'com.datastax.spark.connector.CassandraSparkExtensions').\\\n",
     "    config('spark.sql.catalog.mycatalog', 'com.datastax.spark.connector.datasource.CassandraCatalog').\\\n",
     "    config('spark.cassandra.connection.port', '9042').getOrCreate()\n",
-    "# Some warnings are to be expected."
+    "# Some warnings are to be expected.\n",
+    "# If running this cell does not give any output after ~30 seconds, there is likely an error in the configuration (JAVA_HOME, HADOOP_HOME, etc.)."
    ]
   },
   {
@@ -304,7 +305,9 @@
     "## Write data to Cassandra\n",
     "- One can append or overwrite data in existing database tables.\n",
     "- PySpark is picky regarding data formats.\n",
-    "    - Reading data from the existing table and extracting formatting is possible."
+    "    - Reading data from the existing table and extracting formatting is possible.\n",
+    "- PySpark is case sensitive, while Cassandra is not by default.\n",
+    "    - See example of case sensitvity issues in the [Cassandra notebook](./3_Cassandra.ipynb)."
    ]
   },
   {
@@ -414,7 +417,7 @@
  "metadata": {
   "celltoolbar": "Slideshow",
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "IND320_2024",
    "language": "python",
    "name": "python3"
   },