cogstack search scripts for large data extractions to df

Author: antsh3k

search/search_template.ipynb

@@ -0,0 +1,220 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Seaching CogStack\n",
+    "\n",
+    "This script is designed to be a template for cogstack searches"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "sys.path.append('..')\n",
+    "from credentials import *\n",
+    "from cogstack import CogStack"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Login and Initialise"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cs = CogStack(hosts, username, password, api=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Check the list of Indices and columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i in cs.elastic.indices.get_mapping().keys():\n",
+    "    print(i)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Check the list of columns in that index\n",
+    "index = ''\n",
+    "for col in cs.elastic.indices.get_mapping(index=index)[index]['mappings']['properties'].keys():\n",
+    "    print(col)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Set parameters"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pt_list = []  # example list of patients' patient_TrustNumber here"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Columns of interest\n",
+    "\n",
+    "Select your fields and list in order of output columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "columns = []"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Build query\n",
+    "\n",
+    "For further information on [how to build a query can be found here](https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-simple-query-string-query.html)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Example query structure\n",
+    "query = {\n",
+    "    \"from\": 0,\n",
+    "    \"size\": 10000,\n",
+    "    \"query\": {\n",
+    "        \"bool\": {\n",
+    "            \"filter\": {\n",
+    "                \"terms\": {\"patient_TrustNumber\": pt_list}\n",
+    "            },\n",
+    "            \"must\": [\n",
+    "                {\"query_string\": {\n",
+    "                    \"query\": \"***YOUR LUCENE QUERY HERE***\"}\n",
+    "                }\n",
+    "            ]\n",
+    "        }\n",
+    "    },\n",
+    "    \"_source\": columns  # This is a search column filter. remove if all columns are to be retrieved\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# Search, Process, and Save"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = cs.cogstack2df(query=query, index=index, column_headers=columns)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Process"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Whatever you want here\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Save"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "file_name = \"file_name.csv\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.to_csv(file_name, index=False)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}