{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Setup"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"# Open Alteryx XML into a string \n",
"import polars as pl \n",
"import xml.etree.ElementTree as ET\n",
"\n",
"xml_file_path = \"./SimpleWorkflow/SimpleWorkflow.yxmd\"\n",
"tree = ET.parse(xml_file_path)\n",
"root = tree.getroot()\n",
"\n",
"xml_string = ET.tostring(root, encoding='unicode')\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"('1', 'TextInput (1)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n 1\\n 4\\n \\n \\n 2\\n 5\\n \\n \\n 3\\n 6\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('2', 'AlteryxSelect (2)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('3', 'BrowseV2 (3)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_9b8a61f4c39b2e4ea05f98886a386376~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('4', 'TextInput (4)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n 5\\n 8\\n z\\n a\\n \\n \\n 6\\n 9\\n b\\n d\\n \\n \\n 7\\n 10\\n c\\n c\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('5', 'AlteryxSelect (5)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('6', 'Formula (6)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n MoreCount = [Count] + 10\\n\\n \\n \\n \\n \\n \\n ')\n",
"('7', 'Join (7)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('10', 'BrowseV2 (10)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_c1d268f486209c40bdc02a676a529ee0~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('11', 'Formula (11)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n Path = [Engine.TempFilePath]\\n\\n \\n \\n \\n \\n \\n ')\n",
"('12', 'Sample (12)', '\\n \\n \\n \\n \\n \\n First\\n 1\\n \\n \\n \\n \\n First 1\\n \\n \\n \\n \\n \\n ')\n",
"('13', 'BrowseV2 (13)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_4d6ee2d9de8fac4095ab55a2bceed63e~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('14', 'DbFileOutput (14)', '\\n \\n \\n \\n \\n \\n .\\\\SimpleWorkflowOut.csv\\n \\n \\n CRLF\\n ,\\n False\\n True\\n 28591\\n True\\n \\n \\n \\n \\n \\n SimpleWorkflowOut.csv\\n \\n \\n \\n \\n \\n ')\n",
"('15', 'TextInput (15)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n a\\n a\\n 4\\n \\n \\n b\\n d\\n 6\\n \\n \\n c\\n z\\n 7\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('16', 'HamCheeseJoin', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n HamCheeseJoin\\n HamCheeseJoin\\n \\n \\n \\n \\n \\n ')\n",
"('17', 'BrowseV2 (17)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_e692dab3020ec84ebe69a5de3e6990c9~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('18', 'BrowseV2 (18)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_83aac5fa43df8044b1161f8298a2a180~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('19', 'BrowseV2 (19)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_c2ab20e4f5222342bc00e6424dbc38bd~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n"
]
}
],
"source": [
"# Parse out nodes (tool data) into a dict\n",
"def extract_tool_id_and_contents(xml_string):\n",
" root = ET.fromstring(xml_string)\n",
" results = []\n",
" for node in root.iter('Node'):\n",
" tool_type = node.find('GuiSettings').get('Plugin').split('.')[-1]\n",
" # print('tool type:',tool_type)\n",
" tool_id = node.attrib.get('ToolID')\n",
"\n",
" tool_name = node.find('Properties/Annotation/Name').text\n",
" if not tool_name:\n",
" tool_name = tool_type + \" (\" + tool_id + \")\"\n",
"\n",
" content = ET.tostring(node, encoding='unicode')\n",
" results.append((tool_id, tool_name, content))\n",
" return results\n",
"\n",
"results = extract_tool_id_and_contents(xml_string)\n",
"\n",
"\n",
"for tool in results:\n",
" print(tool)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Tool Functions"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"def tool_select(col_spec: dict):\n",
" \"\"\" Generates select tool code\"\"\"\n",
" dynamic_code = \"df_output = df.with_columns(\\n\"\n",
" dynamic_code_suffix = ''\n",
" for old_name, (new_name, type, selected) in col_spec.items():\n",
"\n",
" if old_name == '*Unknown':\n",
" break \n",
" \n",
" if new_name:\n",
" alias = f\".alias('{new_name}')\"\n",
" dynamic_code_suffix += f\"df_output = df_output.drop(f'{old_name}')\\n\"\n",
" else:\n",
" alias = ''\n",
"\n",
" if type is not None:\n",
" if 'Int' in type:\n",
" cast = f\".cast(pl.{pl.Int64})\"\n",
" elif 'String' in type:\n",
" cast = f\".cast(pl.{pl.String})\"\n",
" else:\n",
" cast = ''\n",
"\n",
" if selected != 'False':\n",
" dynamic_code += f\"df.select(pl.col(f'{old_name}'){cast}{alias}),\\n\"\n",
" else:\n",
" dynamic_code_suffix += f\"df_output = df_output.drop(f'{old_name}')\\n\"\n",
"\n",
" dynamic_code += \")\\n\" + dynamic_code_suffix\n",
" \n",
" return dynamic_code"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"L: shape: (2, 4)\n",
"┌──────────┬──────────┬─────┬────────┐\n",
"│ Column 3 ┆ Column 4 ┆ Ham ┆ Cheese │\n",
"│ --- ┆ --- ┆ --- ┆ --- │\n",
"│ str ┆ str ┆ str ┆ str │\n",
"╞══════════╪══════════╪═════╪════════╡\n",
"│ 5 ┆ 8 ┆ z ┆ a │\n",
"│ 7 ┆ 10 ┆ c ┆ c │\n",
"└──────────┴──────────┴─────┴────────┘\n",
"J: shape: (1, 7)\n",
"┌──────────┬──────────┬─────┬────────┬───────────┬──────────────┬───────┐\n",
"│ Column 3 ┆ Column 4 ┆ Ham ┆ Cheese ┆ Ham_right ┆ Cheese_right ┆ Count │\n",
"│ --- ┆ --- ┆ --- ┆ --- ┆ --- ┆ --- ┆ --- │\n",
"│ str ┆ str ┆ str ┆ str ┆ str ┆ str ┆ str │\n",
"╞══════════╪══════════╪═════╪════════╪═══════════╪══════════════╪═══════╡\n",
"│ 6 ┆ 9 ┆ b ┆ d ┆ b ┆ d ┆ 6 │\n",
"└──────────┴──────────┴─────┴────────┴───────────┴──────────────┴───────┘\n",
"R: shape: (2, 3)\n",
"┌─────┬────────┬───────┐\n",
"│ Ham ┆ Cheese ┆ Count │\n",
"│ --- ┆ --- ┆ --- │\n",
"│ str ┆ str ┆ str │\n",
"╞═════╪════════╪═══════╡\n",
"│ a ┆ a ┆ 4 │\n",
"│ c ┆ z ┆ 7 │\n",
"└─────┴────────┴───────┘\n"
]
}
],
"source": [
"def tool_join(join_spec: dict, df_L: pl.DataFrame, df_R: pl.DataFrame):\n",
" \"\"\" Generates join tool code \"\"\"\n",
" # dynamic_code = \"df_output = df_L.with_columns(\\n\"\n",
" pass\n",
"\n",
" \n",
"\n",
"\n",
"\n",
"# Join spec\n",
"xml_join_tool = results[6][2]\n",
"join_spec = getConf_Join(xml_join_tool)\n",
"\n",
"# Input L: TextInput 4\n",
"In_L = input_textInput(results[3][2])\n",
"# Input R: TextInput 15\n",
"In_R = input_textInput(results[12][2])\n",
"\n",
"# print(join_spec)\n",
"# print(In_L, In_R)\n",
"\n",
"\n",
"## Out L\n",
"# Column 3\tColumn 4\tHam\tCheese\n",
"# 7\t 10\t c\tc\n",
"# 5\t 8\t z\ta\n",
"\n",
"## Out J\n",
"# Column 3\tColumn 4\tHam\tCheese\tRight_Ham\tRight_Cheese\tCount\n",
"# 6\t 9\t b\td\t b\t d\t 6\n",
"\n",
"## Out R\n",
"# Ham\tCheese\tCount\n",
"# a\t a\t 4\n",
"# c\t z\t 7\n",
"\n",
"\n",
"print(\"L:\", In_L.join(In_R, on=join_spec['joinParams'], how='anti'))\n",
"\n",
"print(\"J:\", In_L.join(In_R, on=join_spec['joinParams'], how='inner', coalesce=False))\n",
"\n",
"print(\"R:\", In_R.join(In_L, on=join_spec['joinParams'], how='anti'))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"L in: shape: (3, 3)\n",
"┌─────┬─────┬─────┐\n",
"│ foo ┆ bar ┆ ham │\n",
"│ --- ┆ --- ┆ --- │\n",
"│ i64 ┆ f64 ┆ str │\n",
"╞═════╪═════╪═════╡\n",
"│ 1 ┆ 6.0 ┆ a │\n",
"│ 2 ┆ 7.0 ┆ b │\n",
"│ 3 ┆ 8.0 ┆ c │\n",
"└─────┴─────┴─────┘\n",
"R in: shape: (3, 2)\n",
"┌───────┬─────┐\n",
"│ apple ┆ ham │\n",
"│ --- ┆ --- │\n",
"│ str ┆ str │\n",
"╞═══════╪═════╡\n",
"│ x ┆ a │\n",
"│ y ┆ b │\n",
"│ z ┆ d │\n",
"└───────┴─────┘\n",
"L: shape: (1, 3)\n",
"┌─────┬─────┬─────┐\n",
"│ foo ┆ bar ┆ ham │\n",
"│ --- ┆ --- ┆ --- │\n",
"│ i64 ┆ f64 ┆ str │\n",
"╞═════╪═════╪═════╡\n",
"│ 3 ┆ 8.0 ┆ c │\n",
"└─────┴─────┴─────┘\n"
]
}
],
"source": [
"df = pl.DataFrame(\n",
" {\n",
" \"foo\": [1, 2, 3],\n",
" \"bar\": [6.0, 7.0, 8.0],\n",
" \"ham\": [\"a\", \"b\", \"c\"],\n",
" }\n",
")\n",
"\n",
"other_df = pl.DataFrame(\n",
" {\n",
" \"apple\": [\"x\", \"y\", \"z\"],\n",
" \"ham\": [\"a\", \"b\", \"d\"],\n",
" }\n",
")\n",
"\n",
"print(\"L in:\", df)\n",
"\n",
"print(\"R in:\", other_df)\n",
"\n",
"print(\"L:\", df.join(other_df, left_on=\"ham\", right_on=\"ham\", how='anti'))\n",
"\n",
"# print(\"J: \", df.join(other_df, on=\"ham\", how='inner'))\n",
"\n",
"# print(\"R:\", other_df.join(df, on=\"ham\", how='anti'))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Parsing Tool Config data"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"def input_textInput(xml_string):\n",
" # Get XML for a Text input tool\n",
" root = ET.fromstring(xml_string)\n",
" # Extract the field names\n",
" fields = [field.attrib['name'] for field in root.findall(\".//Fields/Field\")]\n",
" # Extract the data rows\n",
" data_rows = [[c.text for c in row.findall(\"c\")] for row in root.findall(\".//Data/r\")]\n",
" # Create the polars dataframe\n",
" df = pl.DataFrame(data_rows, fields, orient=\"row\")\n",
" # Display the dataframe\n",
" return df"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"def getConf_Select(xml_string):\n",
" root = ET.fromstring(xml_string)\n",
" dict_SelectTool = {}\n",
"\n",
" for field in root.findall(\".//SelectFields/SelectField\"):\n",
" field_name = field.attrib['field']\n",
" field_selected = field.attrib['selected']\n",
"\n",
" try:\n",
" field_type = field.attrib['type']\n",
" except:\n",
" field_type = None\n",
" try:\n",
" field_rename = field.attrib['rename']\n",
" except:\n",
" field_rename = None\n",
"\n",
" dict_SelectTool[field_name] = (field_rename, field_type, field_selected)\n",
"\n",
" return dict_SelectTool"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'joinParams': ['Ham', 'Cheese'], 'fields': {'Right_Ham': ['Right_Ham', 'Right_', None, None], 'Right_Cheese': ['Right_Cheese', 'Right_', None, None], 'Right_Column 3': ['Right_Column 3', 'Right_', 'V_String', '11'], 'Right_Column 4': ['Right_Column 4', 'Right_', 'Int64', '8']}}\n"
]
}
],
"source": [
"def getConf_Join(xml_string):\n",
" root = ET.fromstring(xml_string)\n",
" dict_JoinTool = {}\n",
"\n",
" # Join parameters\n",
" for joinField in root.findall(\".//Configuration/JoinInfo\"):\n",
" if joinField.attrib['connection'] == \"Left\":\n",
" left_on = [field.attrib['field'] for field in joinField]\n",
" if joinField.attrib['connection'] == \"Right\":\n",
" right_on = [field.attrib['field'] for field in joinField]\n",
"\n",
" if left_on == right_on:\n",
" dict_JoinTool['joinParams'] = (left_on)\n",
" else:\n",
" dict_JoinTool['joinParams'] = (left_on, right_on)\n",
"\n",
" \n",
" # Field Parameters\n",
" fieldConfig = {}\n",
" for fields in root.findall(\".//SelectField\"):\n",
" result = []\n",
" if fields.attrib['selected'] == 'True':\n",
" for field in ['rename', 'input', 'type', 'size']:\n",
" try:\n",
" result.append(fields.attrib[field])\n",
" except KeyError:\n",
" result.append(None)\n",
"\n",
" if fields.attrib['field'] != '*Unknown':\n",
" fieldConfig[fields.attrib['field']] = result\n",
"\n",
" dict_JoinTool['fields'] = fieldConfig\n",
"\n",
" return dict_JoinTool\n",
"\n",
"print(getConf_Join(xml_join_tool))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Working with the XML file"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"ename": "ParseError",
"evalue": "syntax error: line 1, column 0 ()",
"output_type": "error",
"traceback": [
"Traceback \u001b[1;36m(most recent call last)\u001b[0m:\n",
"\u001b[0m File \u001b[0;32mc:\\Users\\casey.morter\\AppData\\Local\\miniconda3\\envs\\polaryx\\Lib\\site-packages\\IPython\\core\\interactiveshell.py:3577\u001b[0m in \u001b[0;35mrun_code\u001b[0m\n exec(code_obj, self.user_global_ns, self.user_ns)\u001b[0m\n",
"\u001b[0m Cell \u001b[0;32mIn[11], line 6\u001b[0m\n ToolType = ET.fromstring(ToolXML).find(\".//GuiSettings\").attrib['Plugin'].split(\".\")[2]\u001b[0m\n",
"\u001b[1;36m File \u001b[1;32mc:\\Users\\casey.morter\\AppData\\Local\\miniconda3\\envs\\polaryx\\Lib\\xml\\etree\\ElementTree.py:1335\u001b[1;36m in \u001b[1;35mXML\u001b[1;36m\n\u001b[1;33m parser.feed(text)\u001b[1;36m\n",
"\u001b[1;36m File \u001b[1;32m\u001b[1;36m\u001b[0m\n\u001b[1;31mParseError\u001b[0m\u001b[1;31m:\u001b[0m syntax error: line 1, column 0\n"
]
}
],
"source": [
"# Parse all tools in tools dict\n",
"for tool in results:\n",
"\n",
" ToolID = tool[0]\n",
" ToolXML = tool[1]\n",
" ToolType = ET.fromstring(ToolXML).find(\".//GuiSettings\").attrib['Plugin'].split(\".\")[2]\n",
"\n",
" print(ToolID, ToolType)\n",
"\n",
" if ToolType == 'TextInput':\n",
" print(input_textInput(ToolXML))"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"############### Input dataframe (TextInput):\n",
" shape: (3, 4)\n",
"┌──────────┬──────────┬─────┬────────┐\n",
"│ Column 3 ┆ Column 4 ┆ Ham ┆ Cheese │\n",
"│ --- ┆ --- ┆ --- ┆ --- │\n",
"│ str ┆ str ┆ str ┆ str │\n",
"╞══════════╪══════════╪═════╪════════╡\n",
"│ 5 ┆ 8 ┆ z ┆ a │\n",
"│ 6 ┆ 9 ┆ b ┆ d │\n",
"│ 7 ┆ 10 ┆ c ┆ c │\n",
"└──────────┴──────────┴─────┴────────┘\n",
"\n",
"############### Generated code from Select tool: \n",
" df_output = df.with_columns(\n",
"df.select(pl.col(f'Column 3').alias('Col_3_renamed')),\n",
")\n",
"df_output = df_output.drop(f'Column 3')\n",
"df_output = df_output.drop(f'Column 4')\n",
"\n",
"\n",
"############### Output DF: \n",
"\n",
" shape: (3, 3)\n",
"┌─────┬────────┬───────────────┐\n",
"│ Ham ┆ Cheese ┆ Col_3_renamed │\n",
"│ --- ┆ --- ┆ --- │\n",
"│ str ┆ str ┆ str │\n",
"╞═════╪════════╪═══════════════╡\n",
"│ z ┆ a ┆ 5 │\n",
"│ b ┆ d ┆ 6 │\n",
"│ c ┆ c ┆ 7 │\n",
"└─────┴────────┴───────────────┘\n"
]
}
],
"source": [
"# Tool 1: TextInput\n",
"xml_tool1 = results[3][2]\n",
"df_in = input_textInput(xml_tool1)\n",
"print(\"\\n############### Input dataframe (TextInput):\\n\", df_in)\n",
"# Tool 2: Select\n",
"col_spec = getConf_Select(results[4][2])\n",
"# Generate code from \n",
"code = tool_select(col_spec)\n",
"print(\"\\n############### Generated code from Select tool: \\n\", code)\n",
"# Execute and display output\n",
"df = df_in\n",
"exec(code)\n",
"print(\"\\n############### Output DF: \\n\\n\", df_output)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"('1', 'TextInput (1)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n 1\\n 4\\n \\n \\n 2\\n 5\\n \\n \\n 3\\n 6\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('2', 'AlteryxSelect (2)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('3', 'BrowseV2 (3)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_9b8a61f4c39b2e4ea05f98886a386376~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('4', 'TextInput (4)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n 5\\n 8\\n z\\n a\\n \\n \\n 6\\n 9\\n b\\n d\\n \\n \\n 7\\n 10\\n c\\n c\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('5', 'AlteryxSelect (5)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('6', 'Formula (6)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n MoreCount = [Count] + 10\\n\\n \\n \\n \\n \\n \\n ')\n",
"('7', 'Join (7)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('10', 'BrowseV2 (10)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_c1d268f486209c40bdc02a676a529ee0~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('11', 'Formula (11)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n Path = [Engine.TempFilePath]\\n\\n \\n \\n \\n \\n \\n ')\n",
"('12', 'Sample (12)', '\\n \\n \\n \\n \\n \\n First\\n 1\\n \\n \\n \\n \\n First 1\\n \\n \\n \\n \\n \\n ')\n",
"('13', 'BrowseV2 (13)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_4d6ee2d9de8fac4095ab55a2bceed63e~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('14', 'DbFileOutput (14)', '\\n \\n \\n \\n \\n \\n .\\\\SimpleWorkflowOut.csv\\n \\n \\n CRLF\\n ,\\n False\\n True\\n 28591\\n True\\n \\n \\n \\n \\n \\n SimpleWorkflowOut.csv\\n \\n \\n \\n \\n \\n ')\n",
"('15', 'TextInput (15)', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n a\\n a\\n 4\\n \\n \\n b\\n d\\n 6\\n \\n \\n c\\n z\\n 7\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('16', 'HamCheeseJoin', '\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n HamCheeseJoin\\n HamCheeseJoin\\n \\n \\n \\n \\n \\n ')\n",
"('17', 'BrowseV2 (17)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_e692dab3020ec84ebe69a5de3e6990c9~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('18', 'BrowseV2 (18)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_83aac5fa43df8044b1161f8298a2a180~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n",
"('19', 'BrowseV2 (19)', '\\n \\n \\n \\n \\n \\n C:\\\\Users\\\\casey.morter\\\\AppData\\\\Local\\\\Temp\\\\Engine_28104_a89278053b87e446bfe970eb948f1ef4_\\\\Engine_28104_c2ab20e4f5222342bc00e6424dbc38bd~.yxdb\\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n \\n ')\n"
]
}
],
"source": [
"for tool in results:\n",
" print(tool)"
]
},
{
"cell_type": "markdown",
"metadata": {
"vscode": {
"languageId": "latex"
}
},
"source": [
"# DAG Analysis"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: networkx in c:\\users\\casey.morter\\appdata\\local\\miniconda3\\lib\\site-packages (2.8.8)\n",
"Requirement already satisfied: matplotlib in c:\\users\\casey.morter\\appdata\\local\\miniconda3\\lib\\site-packages (3.7.1)\n",
"Requirement already satisfied: pyparsing>=2.3.1 in c:\\users\\casey.morter\\appdata\\local\\miniconda3\\lib\\site-packages (from matplotlib) (3.0.9)\n",
"Requirement already satisfied: numpy>=1.20 in c:\\users\\casey.morter\\appdata\\local\\miniconda3\\lib\\site-packages (from matplotlib) (1.24.2)\n",
"Requirement already satisfied: python-dateutil>=2.7 in c:\\users\\casey.morter\\appdata\\local\\miniconda3\\lib\\site-packages (from matplotlib) (2.8.2)\n",
"Requirement already satisfied: cycler>=0.10 in c:\\users\\casey.morter\\appdata\\local\\miniconda3\\lib\\site-packages (from matplotlib) (0.11.0)\n",
"Requirement already satisfied: pillow>=6.2.0 in c:\\users\\casey.morter\\appdata\\local\\miniconda3\\lib\\site-packages (from matplotlib) (9.4.0)\n",
"Requirement already satisfied: kiwisolver>=1.0.1 in c:\\users\\casey.morter\\appdata\\local\\miniconda3\\lib\\site-packages (from matplotlib) (1.4.4)\n",
"Requirement already satisfied: contourpy>=1.0.1 in c:\\users\\casey.morter\\appdata\\local\\miniconda3\\lib\\site-packages (from matplotlib) (1.0.7)\n",
"Requirement already satisfied: packaging>=20.0 in c:\\users\\casey.morter\\appdata\\local\\miniconda3\\lib\\site-packages (from matplotlib) (24.0)\n",
"Requirement already satisfied: fonttools>=4.22.0 in c:\\users\\casey.morter\\appdata\\local\\miniconda3\\lib\\site-packages (from matplotlib) (4.39.0)\n",
"Requirement already satisfied: six>=1.5 in c:\\users\\casey.morter\\appdata\\local\\miniconda3\\lib\\site-packages (from python-dateutil>=2.7->matplotlib) (1.16.0)\n",
"Note: you may need to restart the kernel to use updated packages.\n"
]
}
],
"source": [
"%pip install networkx matplotlib"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import xml.etree.ElementTree as ET\n",
"import networkx as nx\n",
"import matplotlib.pyplot as plt\n",
"\n",
"def visualize_dag(xml_string):\n",
" # Parse the XML string\n",
" root = ET.fromstring(xml_string)\n",
"\n",
" # Create a directed graph\n",
" G = nx.DiGraph()\n",
"\n",
" # Add edges to the graph\n",
" for conn in root.findall('Connection'):\n",
" origin = conn.find('Origin')\n",
" destination = conn.find('Destination')\n",
" \n",
" origin_id = origin.get('ToolID')\n",
" dest_id = destination.get('ToolID')\n",
" origin_conn = origin.get('Connection')\n",
" dest_conn = destination.get('Connection')\n",
" \n",
" G.add_edge(origin_id, dest_id)\n",
" G.edges[origin_id, dest_id]['origin_conn'] = origin_conn\n",
" G.edges[origin_id, dest_id]['dest_conn'] = dest_conn\n",
"\n",
" # Set up the plot\n",
" plt.figure(figsize=(12, 8))\n",
" pos = nx.spring_layout(G)\n",
"\n",
" # Draw nodes\n",
" nx.draw_networkx_nodes(G, pos, node_size=2000, node_color='lightblue')\n",
" nx.draw_networkx_labels(G, pos, labels={node: f\"Tool ID: {node}\" for node in G.nodes()})\n",
"\n",
" # Draw edges\n",
" nx.draw_networkx_edges(G, pos, edge_color='gray', arrows=True, arrowsize=20)\n",
"\n",
" # Add edge labels\n",
" edge_labels = {(u, v): f\"{d['origin_conn']} -> {d['dest_conn']}\" for u, v, d in G.edges(data=True)}\n",
" nx.draw_networkx_edge_labels(G, pos, edge_labels=edge_labels, font_size=8)\n",
"\n",
" # Remove axis\n",
" plt.axis('off')\n",
"\n",
" # Show the plot\n",
" plt.tight_layout()\n",
" plt.show()\n",
"\n",
"# Example usage:\n",
"xml_string = \"\"\"\n",
"\n",
" \n",
"\n",
"\"\"\"\n",
"visualize_dag(xml_string)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 2
}