Plotting

demo/pandas_plotting.ipynb

@@ -0,0 +1,137 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "f9661021-bfa6-485a-a735-2b5d06006063",
+   "metadata": {},
+   "source": [
+    "# Plotting\n",
+    "In this notebook we ask Bob to draw a plot from a given pandas Dataframe. It uses seaborn under the hood."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "31c311c0-5a8f-4bd5-a6ff-a63d151f9b21",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from bia_bob import bob"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "b9805072-55f2-4ad0-af18-d4b4ac4e7f42",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "6e590509-a159-4fa4-9ecf-1ad8ccb597ac",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "df = pd.DataFrame({\n",
+    "    'x':[1,2,3,4,5,6],\n",
+    "    'y':[1,1,2,2,3,4]\n",
+    "})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "e732fd57-73ec-4c34-85cc-fbd60bba4c32",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "bob.initialize(globals())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "359d68fc-112f-4a5a-859b-db19eb6aa04e",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Axes: xlabel='x', ylabel='y'>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/markdown": [
+       "Here is the plot of x against y in the dataframe df."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "%bob Please draw a plot of x against y in the dataframe df."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c24112f8-afc6-40f3-af67-f5fd48ba758c",
+   "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": "3.9.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

setup.cfg

@@ -36,6 +36,9 @@ install_requires =
     langchain>=0.0.251
     stackview>=0.6.3
     napari-segment-blobs-and-things-with-membranes>=0.3.6
+    napari-skimage-regionprops
+    pandas
+    seaborn
 
 python_requires = >=3.8
 include_package_data = True

src/bia_bob/_machinery.py

@@ -58,7 +58,12 @@ def init_assistant(variables, temperature=0):
     MEMORY_KEY = "chat_history"
     _context.memory = ConversationBufferMemory(memory_key=MEMORY_KEY, return_messages=True)
 
-    system_message = SystemMessage(content="You are a powerful assistant. After a function has been called to do a task, there is no need do the task again unless the human explicitly asks for it. Answer the human's questions below.")
+    system_message = SystemMessage(content="""
+    You never produce sample data.
+    You never print out dataframes.
+    Do not answer questions that are not asked.
+    Answer the human's questions below and keep your answers short.
+    """)
     agent_kwargs = {
         "system_message": system_message,
         "extra_prompt_messages": [MessagesPlaceholder(variable_name=MEMORY_KEY)],
@@ -71,6 +76,7 @@ def init_assistant(variables, temperature=0):
         agent_kwargs=agent_kwargs,
         memory=_context.memory,
     )
+
     # store the variables
     _context.variables = variables