diff --git a/ipython_script/analyse_wf_march_22.ipynb b/ipython_script/analyse_wf_march_22.ipynb
new file mode 100644
index 0000000..9b97ad5
--- /dev/null
+++ b/ipython_script/analyse_wf_march_22.ipynb
@@ -0,0 +1,1822 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "id": "6f18f94d-2489-42d6-a9e7-172c8fadd39f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "id": "ad85fbb3-57aa-49b5-a5d9-8f9d63321309",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "wf_path = \"../data/workflow-connections_Feb_22_1.csv\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "id": "0d460c01-3cde-4163-9764-220dc5db00ae",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/anupkumar/anaconda3/envs/tool_prediction_gru_wc/lib/python3.6/site-packages/IPython/core/interactiveshell.py:3072: DtypeWarning: Columns (0,2,5) have mixed types.Specify dtype option on import or set low_memory=False.\n",
+      "  interactivity=interactivity, compiler=compiler, result=result)\n"
+     ]
+    }
+   ],
+   "source": [
+    "wf_frame = pd.read_csv(wf_path, sep=\"|\", header=None)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "id": "23807c0e-abaf-4496-99d6-bbfaa784d8f8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>0</th>\n",
+       "      <th>1</th>\n",
+       "      <th>2</th>\n",
+       "      <th>3</th>\n",
+       "      <th>4</th>\n",
+       "      <th>5</th>\n",
+       "      <th>6</th>\n",
+       "      <th>7</th>\n",
+       "      <th>8</th>\n",
+       "      <th>9</th>\n",
+       "      <th>10</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>wf_id</td>\n",
+       "      <td>wf_updated</td>\n",
+       "      <td>in_id</td>\n",
+       "      <td>...</td>\n",
+       "      <td>in_tool_v</td>\n",
+       "      <td>out_id</td>\n",
+       "      <td>...</td>\n",
+       "      <td>out_tool_v</td>\n",
+       "      <td>published</td>\n",
+       "      <td>deleted</td>\n",
+       "      <td>has_errors</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>--------+------------+---------+--------------...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>2013-02-07</td>\n",
+       "      <td>5</td>\n",
+       "      <td>Grep1                                        ...</td>\n",
+       "      <td>1.0.1</td>\n",
+       "      <td>7</td>\n",
+       "      <td>Remove beginning1                            ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3</td>\n",
+       "      <td>2013-02-07</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Cut1                                         ...</td>\n",
+       "      <td>1.0.1</td>\n",
+       "      <td>8</td>\n",
+       "      <td>addValue                                     ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>3</td>\n",
+       "      <td>2013-02-07</td>\n",
+       "      <td>7</td>\n",
+       "      <td>Remove beginning1                            ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Cut1                                         ...</td>\n",
+       "      <td>1.0.1</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2412941</th>\n",
+       "      <td>134921</td>\n",
+       "      <td>2022-02-15</td>\n",
+       "      <td>1.9924e+06</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>1.99235e+06</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/pjbriggs/trimmom...</td>\n",
+       "      <td>0.38.1</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2412942</th>\n",
+       "      <td>134921</td>\n",
+       "      <td>2022-02-15</td>\n",
+       "      <td>1.99240e+06</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>1.99235e+06</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/pjbriggs/trimmom...</td>\n",
+       "      <td>0.38.1</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2412943</th>\n",
+       "      <td>134921</td>\n",
+       "      <td>2022-02-15</td>\n",
+       "      <td>1.99241e+06</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>1.99235e+06</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/pjbriggs/trimmom...</td>\n",
+       "      <td>0.38.1</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2412944</th>\n",
+       "      <td>134921</td>\n",
+       "      <td>2022-02-15</td>\n",
+       "      <td>1.99241e+06</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>1.99236e+06</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/devteam/bowtie2/...</td>\n",
+       "      <td>2.4.2+galaxy0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2412945</th>\n",
+       "      <td>(2412943 rows)</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>2412946 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                                        0             1   \\\n",
+       "0                                                  wf_id     wf_updated    \n",
+       "1        --------+------------+---------+--------------...           NaN   \n",
+       "2                                                       3    2013-02-07    \n",
+       "3                                                       3    2013-02-07    \n",
+       "4                                                       3    2013-02-07    \n",
+       "...                                                    ...           ...   \n",
+       "2412941                                            134921    2022-02-15    \n",
+       "2412942                                            134921    2022-02-15    \n",
+       "2412943                                            134921    2022-02-15    \n",
+       "2412944                                            134921    2022-02-15    \n",
+       "2412945                                     (2412943 rows)           NaN   \n",
+       "\n",
+       "                  2                                                  3   \\\n",
+       "0            in_id                                                  ...   \n",
+       "1                NaN                                                NaN   \n",
+       "2                 5    Grep1                                        ...   \n",
+       "3                 6    Cut1                                         ...   \n",
+       "4                 7    Remove beginning1                            ...   \n",
+       "...              ...                                                ...   \n",
+       "2412941   1.9924e+06                                                ...   \n",
+       "2412942  1.99240e+06                                                ...   \n",
+       "2412943  1.99241e+06                                                ...   \n",
+       "2412944  1.99241e+06                                                ...   \n",
+       "2412945          NaN                                                NaN   \n",
+       "\n",
+       "                                                     4            5   \\\n",
+       "0                          in_tool_v                        out_id     \n",
+       "1                                                   NaN          NaN   \n",
+       "2         1.0.1                                                   7    \n",
+       "3         1.0.1                                                   8    \n",
+       "4         1.0.0                                                   6    \n",
+       "...                                                 ...          ...   \n",
+       "2412941                                                  1.99235e+06   \n",
+       "2412942                                                  1.99235e+06   \n",
+       "2412943                                                  1.99235e+06   \n",
+       "2412944                                                  1.99236e+06   \n",
+       "2412945                                             NaN          NaN   \n",
+       "\n",
+       "                                                        6   \\\n",
+       "0                                                      ...   \n",
+       "1                                                      NaN   \n",
+       "2         Remove beginning1                            ...   \n",
+       "3         addValue                                     ...   \n",
+       "4         Cut1                                         ...   \n",
+       "...                                                    ...   \n",
+       "2412941   toolshed.g2.bx.psu.edu/repos/pjbriggs/trimmom...   \n",
+       "2412942   toolshed.g2.bx.psu.edu/repos/pjbriggs/trimmom...   \n",
+       "2412943   toolshed.g2.bx.psu.edu/repos/pjbriggs/trimmom...   \n",
+       "2412944   toolshed.g2.bx.psu.edu/repos/devteam/bowtie2/...   \n",
+       "2412945                                                NaN   \n",
+       "\n",
+       "                                                     7            8   \\\n",
+       "0                          out_tool_v                     published    \n",
+       "1                                                   NaN          NaN   \n",
+       "2         1.0.0                                           f            \n",
+       "3         1.0.0                                           f            \n",
+       "4         1.0.1                                           f            \n",
+       "...                                                 ...          ...   \n",
+       "2412941   0.38.1                                          f            \n",
+       "2412942   0.38.1                                          f            \n",
+       "2412943   0.38.1                                          f            \n",
+       "2412944   2.4.2+galaxy0                                   f            \n",
+       "2412945                                             NaN          NaN   \n",
+       "\n",
+       "                9             10  \n",
+       "0         deleted    has_errors   \n",
+       "1              NaN           NaN  \n",
+       "2         t                    f  \n",
+       "3         t                    f  \n",
+       "4         t                    f  \n",
+       "...            ...           ...  \n",
+       "2412941   f                    f  \n",
+       "2412942   f                    f  \n",
+       "2412943   f                    f  \n",
+       "2412944   f                    f  \n",
+       "2412945        NaN           NaN  \n",
+       "\n",
+       "[2412946 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 49,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "wf_frame"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "id": "9dd25661-cab1-4a78-8570-cd5696b8bb38",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "wf_frame_1 = wf_frame[1:len(wf_frame.index)-1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "id": "30d18e50-8561-4d8b-869b-2d31ae0cf86a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>0</th>\n",
+       "      <th>1</th>\n",
+       "      <th>2</th>\n",
+       "      <th>3</th>\n",
+       "      <th>4</th>\n",
+       "      <th>5</th>\n",
+       "      <th>6</th>\n",
+       "      <th>7</th>\n",
+       "      <th>8</th>\n",
+       "      <th>9</th>\n",
+       "      <th>10</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>2013-02-07</td>\n",
+       "      <td>5</td>\n",
+       "      <td>Grep1                                        ...</td>\n",
+       "      <td>1.0.1</td>\n",
+       "      <td>7</td>\n",
+       "      <td>Remove beginning1                            ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3</td>\n",
+       "      <td>2013-02-07</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Cut1                                         ...</td>\n",
+       "      <td>1.0.1</td>\n",
+       "      <td>8</td>\n",
+       "      <td>addValue                                     ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>3</td>\n",
+       "      <td>2013-02-07</td>\n",
+       "      <td>7</td>\n",
+       "      <td>Remove beginning1                            ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Cut1                                         ...</td>\n",
+       "      <td>1.0.1</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>3</td>\n",
+       "      <td>2013-02-07</td>\n",
+       "      <td>7</td>\n",
+       "      <td>Remove beginning1                            ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>9</td>\n",
+       "      <td>Cut1                                         ...</td>\n",
+       "      <td>1.0.1</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>3</td>\n",
+       "      <td>2013-02-07</td>\n",
+       "      <td>8</td>\n",
+       "      <td>addValue                                     ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>11</td>\n",
+       "      <td>Paste1                                       ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2412940</th>\n",
+       "      <td>134921</td>\n",
+       "      <td>2022-02-15</td>\n",
+       "      <td>1.9924e+06</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>1.99235e+06</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/iuc/filter_tabul...</td>\n",
+       "      <td>2.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2412941</th>\n",
+       "      <td>134921</td>\n",
+       "      <td>2022-02-15</td>\n",
+       "      <td>1.9924e+06</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>1.99235e+06</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/pjbriggs/trimmom...</td>\n",
+       "      <td>0.38.1</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2412942</th>\n",
+       "      <td>134921</td>\n",
+       "      <td>2022-02-15</td>\n",
+       "      <td>1.99240e+06</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>1.99235e+06</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/pjbriggs/trimmom...</td>\n",
+       "      <td>0.38.1</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2412943</th>\n",
+       "      <td>134921</td>\n",
+       "      <td>2022-02-15</td>\n",
+       "      <td>1.99241e+06</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>1.99235e+06</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/pjbriggs/trimmom...</td>\n",
+       "      <td>0.38.1</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2412944</th>\n",
+       "      <td>134921</td>\n",
+       "      <td>2022-02-15</td>\n",
+       "      <td>1.99241e+06</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>1.99236e+06</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/devteam/bowtie2/...</td>\n",
+       "      <td>2.4.2+galaxy0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>2412943 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "               0             1            2   \\\n",
+       "2              3    2013-02-07            5    \n",
+       "3              3    2013-02-07            6    \n",
+       "4              3    2013-02-07            7    \n",
+       "5              3    2013-02-07            7    \n",
+       "6              3    2013-02-07            8    \n",
+       "...           ...           ...          ...   \n",
+       "2412940   134921    2022-02-15    1.9924e+06   \n",
+       "2412941   134921    2022-02-15    1.9924e+06   \n",
+       "2412942   134921    2022-02-15   1.99240e+06   \n",
+       "2412943   134921    2022-02-15   1.99241e+06   \n",
+       "2412944   134921    2022-02-15   1.99241e+06   \n",
+       "\n",
+       "                                                        3   \\\n",
+       "2         Grep1                                        ...   \n",
+       "3         Cut1                                         ...   \n",
+       "4         Remove beginning1                            ...   \n",
+       "5         Remove beginning1                            ...   \n",
+       "6         addValue                                     ...   \n",
+       "...                                                    ...   \n",
+       "2412940                                                ...   \n",
+       "2412941                                                ...   \n",
+       "2412942                                                ...   \n",
+       "2412943                                                ...   \n",
+       "2412944                                                ...   \n",
+       "\n",
+       "                                                     4            5   \\\n",
+       "2         1.0.1                                                   7    \n",
+       "3         1.0.1                                                   8    \n",
+       "4         1.0.0                                                   6    \n",
+       "5         1.0.0                                                   9    \n",
+       "6         1.0.0                                                  11    \n",
+       "...                                                 ...          ...   \n",
+       "2412940                                                  1.99235e+06   \n",
+       "2412941                                                  1.99235e+06   \n",
+       "2412942                                                  1.99235e+06   \n",
+       "2412943                                                  1.99235e+06   \n",
+       "2412944                                                  1.99236e+06   \n",
+       "\n",
+       "                                                        6   \\\n",
+       "2         Remove beginning1                            ...   \n",
+       "3         addValue                                     ...   \n",
+       "4         Cut1                                         ...   \n",
+       "5         Cut1                                         ...   \n",
+       "6         Paste1                                       ...   \n",
+       "...                                                    ...   \n",
+       "2412940   toolshed.g2.bx.psu.edu/repos/iuc/filter_tabul...   \n",
+       "2412941   toolshed.g2.bx.psu.edu/repos/pjbriggs/trimmom...   \n",
+       "2412942   toolshed.g2.bx.psu.edu/repos/pjbriggs/trimmom...   \n",
+       "2412943   toolshed.g2.bx.psu.edu/repos/pjbriggs/trimmom...   \n",
+       "2412944   toolshed.g2.bx.psu.edu/repos/devteam/bowtie2/...   \n",
+       "\n",
+       "                                                     7            8   \\\n",
+       "2         1.0.0                                           f            \n",
+       "3         1.0.0                                           f            \n",
+       "4         1.0.1                                           f            \n",
+       "5         1.0.1                                           f            \n",
+       "6         1.0.0                                           f            \n",
+       "...                                                 ...          ...   \n",
+       "2412940   2.0.0                                           f            \n",
+       "2412941   0.38.1                                          f            \n",
+       "2412942   0.38.1                                          f            \n",
+       "2412943   0.38.1                                          f            \n",
+       "2412944   2.4.2+galaxy0                                   f            \n",
+       "\n",
+       "                9   10  \n",
+       "2         t          f  \n",
+       "3         t          f  \n",
+       "4         t          f  \n",
+       "5         t          f  \n",
+       "6         t          f  \n",
+       "...            ...  ..  \n",
+       "2412940   f          f  \n",
+       "2412941   f          f  \n",
+       "2412942   f          f  \n",
+       "2412943   f          f  \n",
+       "2412944   f          f  \n",
+       "\n",
+       "[2412943 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 51,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "wf_frame_1 = wf_frame_1[1:]\n",
+    "wf_frame_1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "id": "13182050-3366-4a3b-b121-5c3d4e8555a3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>0</th>\n",
+       "      <th>1</th>\n",
+       "      <th>2</th>\n",
+       "      <th>3</th>\n",
+       "      <th>4</th>\n",
+       "      <th>5</th>\n",
+       "      <th>6</th>\n",
+       "      <th>7</th>\n",
+       "      <th>8</th>\n",
+       "      <th>9</th>\n",
+       "      <th>10</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1910966</th>\n",
+       "      <td>72418</td>\n",
+       "      <td>2020-12-04</td>\n",
+       "      <td>1018284</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/iuc/anndata_mani...</td>\n",
+       "      <td>0.6.22.post1+galaxy1</td>\n",
+       "      <td>1018287</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/iuc/scanpy_plot/...</td>\n",
+       "      <td>1.4.4.post1+galaxy1</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>459259</th>\n",
+       "      <td>1915</td>\n",
+       "      <td>2015-01-19</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1083589</th>\n",
+       "      <td>1915</td>\n",
+       "      <td>2015-01-19</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>252642</th>\n",
+       "      <td>1915</td>\n",
+       "      <td>2015-01-19</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6821</th>\n",
+       "      <td>887</td>\n",
+       "      <td>2014-03-14</td>\n",
+       "      <td>15219</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>15230</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/devteam/fastqc/f...</td>\n",
+       "      <td></td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1592784</th>\n",
+       "      <td>21747</td>\n",
+       "      <td>2018-12-18</td>\n",
+       "      <td>331828</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>331801</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/iuc/stacks_procr...</td>\n",
+       "      <td>1.46.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1590874</th>\n",
+       "      <td>21600</td>\n",
+       "      <td>2018-12-17</td>\n",
+       "      <td>328839</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/galaxyp/openms_m...</td>\n",
+       "      <td>2.2.0</td>\n",
+       "      <td>328835</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/galaxyp/openms_p...</td>\n",
+       "      <td>2.2.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1474236</th>\n",
+       "      <td>5488</td>\n",
+       "      <td>2016-07-29</td>\n",
+       "      <td>81677</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/devteam/get_flan...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>81707</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/devteam/join/gop...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1713787</th>\n",
+       "      <td>39694</td>\n",
+       "      <td>2019-11-21</td>\n",
+       "      <td>597867</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/devteam/bamtools...</td>\n",
+       "      <td>2.4.1</td>\n",
+       "      <td>597868</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/iuc/umi_tools_co...</td>\n",
+       "      <td>0.5.3.2</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2158410</th>\n",
+       "      <td>105860</td>\n",
+       "      <td>2021-08-14</td>\n",
+       "      <td>1556606</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>1556612</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/devteam/fastqc/f...</td>\n",
+       "      <td>0.72+galaxy1</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>2412943 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "               0             1          2   \\\n",
+       "1910966     72418   2020-12-04     1018284   \n",
+       "459259       1915   2015-01-19       29099   \n",
+       "1083589      1915   2015-01-19       29099   \n",
+       "252642       1915   2015-01-19       29099   \n",
+       "6821         887    2014-03-14      15219    \n",
+       "...           ...           ...        ...   \n",
+       "1592784     21747   2018-12-18      331828   \n",
+       "1590874     21600   2018-12-17      328839   \n",
+       "1474236      5488   2016-07-29       81677   \n",
+       "1713787     39694   2019-11-21      597867   \n",
+       "2158410    105860   2021-08-14     1556606   \n",
+       "\n",
+       "                                                        3   \\\n",
+       "1910966   toolshed.g2.bx.psu.edu/repos/iuc/anndata_mani...   \n",
+       "459259    cat1                                         ...   \n",
+       "1083589   cat1                                         ...   \n",
+       "252642    cat1                                         ...   \n",
+       "6821                                                   ...   \n",
+       "...                                                    ...   \n",
+       "1592784                                                ...   \n",
+       "1590874   toolshed.g2.bx.psu.edu/repos/galaxyp/openms_m...   \n",
+       "1474236   toolshed.g2.bx.psu.edu/repos/devteam/get_flan...   \n",
+       "1713787   toolshed.g2.bx.psu.edu/repos/devteam/bamtools...   \n",
+       "2158410                                                ...   \n",
+       "\n",
+       "                                                     4          5   \\\n",
+       "1910966   0.6.22.post1+galaxy1                             1018287   \n",
+       "459259    1.0.0                                              29099   \n",
+       "1083589   1.0.0                                              29099   \n",
+       "252642    1.0.0                                              29099   \n",
+       "6821                                                        15230    \n",
+       "...                                                 ...        ...   \n",
+       "1592784                                                     331801   \n",
+       "1590874   2.2.0                                             328835   \n",
+       "1474236   1.0.0                                              81707   \n",
+       "1713787   2.4.1                                             597868   \n",
+       "2158410                                                    1556612   \n",
+       "\n",
+       "                                                        6   \\\n",
+       "1910966   toolshed.g2.bx.psu.edu/repos/iuc/scanpy_plot/...   \n",
+       "459259    cat1                                         ...   \n",
+       "1083589   cat1                                         ...   \n",
+       "252642    cat1                                         ...   \n",
+       "6821      toolshed.g2.bx.psu.edu/repos/devteam/fastqc/f...   \n",
+       "...                                                    ...   \n",
+       "1592784   toolshed.g2.bx.psu.edu/repos/iuc/stacks_procr...   \n",
+       "1590874   toolshed.g2.bx.psu.edu/repos/galaxyp/openms_p...   \n",
+       "1474236   toolshed.g2.bx.psu.edu/repos/devteam/join/gop...   \n",
+       "1713787   toolshed.g2.bx.psu.edu/repos/iuc/umi_tools_co...   \n",
+       "2158410   toolshed.g2.bx.psu.edu/repos/devteam/fastqc/f...   \n",
+       "\n",
+       "                                                     7            8   \\\n",
+       "1910966   1.4.4.post1+galaxy1                             f            \n",
+       "459259    1.0.0                                           f            \n",
+       "1083589   1.0.0                                           f            \n",
+       "252642    1.0.0                                           f            \n",
+       "6821                                                      f            \n",
+       "...                                                 ...          ...   \n",
+       "1592784   1.46.0                                          f            \n",
+       "1590874   2.2.0                                           f            \n",
+       "1474236   1.0.0                                           f            \n",
+       "1713787   0.5.3.2                                         f            \n",
+       "2158410   0.72+galaxy1                                    f            \n",
+       "\n",
+       "                9   10  \n",
+       "1910966   f          f  \n",
+       "459259    t          f  \n",
+       "1083589   t          f  \n",
+       "252642    t          f  \n",
+       "6821      t             \n",
+       "...            ...  ..  \n",
+       "1592784   f          t  \n",
+       "1590874   f          f  \n",
+       "1474236   t          f  \n",
+       "1713787   f          f  \n",
+       "2158410   f             \n",
+       "\n",
+       "[2412943 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 53,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "wf_frame_1 = wf_frame_1.sample(frac=1)\n",
+    "wf_frame_1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "id": "f1b96941-6fa4-4735-a292-4a19e42fe9f7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>0</th>\n",
+       "      <th>1</th>\n",
+       "      <th>2</th>\n",
+       "      <th>3</th>\n",
+       "      <th>4</th>\n",
+       "      <th>5</th>\n",
+       "      <th>6</th>\n",
+       "      <th>7</th>\n",
+       "      <th>8</th>\n",
+       "      <th>9</th>\n",
+       "      <th>10</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>459259</th>\n",
+       "      <td>1915</td>\n",
+       "      <td>2015-01-19</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1083589</th>\n",
+       "      <td>1915</td>\n",
+       "      <td>2015-01-19</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>252642</th>\n",
+       "      <td>1915</td>\n",
+       "      <td>2015-01-19</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6821</th>\n",
+       "      <td>887</td>\n",
+       "      <td>2014-03-14</td>\n",
+       "      <td>15219</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>15230</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/devteam/fastqc/f...</td>\n",
+       "      <td></td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1229113</th>\n",
+       "      <td>1915</td>\n",
+       "      <td>2015-01-19</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>293631</th>\n",
+       "      <td>1915</td>\n",
+       "      <td>2015-01-19</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>431234</th>\n",
+       "      <td>1915</td>\n",
+       "      <td>2015-01-19</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2299184</th>\n",
+       "      <td>125597</td>\n",
+       "      <td>2022-01-27</td>\n",
+       "      <td>1850173</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>1850165</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/iuc/purge_dups/p...</td>\n",
+       "      <td>1.2.5+galaxy4</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1985563</th>\n",
+       "      <td>84931</td>\n",
+       "      <td>2021-03-18</td>\n",
+       "      <td>1187845</td>\n",
+       "      <td>addValue                                     ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>1187846</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/bgruening/text_p...</td>\n",
+       "      <td>0.1.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>331020</th>\n",
+       "      <td>1915</td>\n",
+       "      <td>2015-01-19</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>29099</td>\n",
+       "      <td>cat1                                         ...</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>4999 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "               0             1          2   \\\n",
+       "459259       1915   2015-01-19       29099   \n",
+       "1083589      1915   2015-01-19       29099   \n",
+       "252642       1915   2015-01-19       29099   \n",
+       "6821         887    2014-03-14      15219    \n",
+       "1229113      1915   2015-01-19       29099   \n",
+       "...           ...           ...        ...   \n",
+       "293631       1915   2015-01-19       29099   \n",
+       "431234       1915   2015-01-19       29099   \n",
+       "2299184    125597   2022-01-27     1850173   \n",
+       "1985563     84931   2021-03-18     1187845   \n",
+       "331020       1915   2015-01-19       29099   \n",
+       "\n",
+       "                                                        3   \\\n",
+       "459259    cat1                                         ...   \n",
+       "1083589   cat1                                         ...   \n",
+       "252642    cat1                                         ...   \n",
+       "6821                                                   ...   \n",
+       "1229113   cat1                                         ...   \n",
+       "...                                                    ...   \n",
+       "293631    cat1                                         ...   \n",
+       "431234    cat1                                         ...   \n",
+       "2299184                                                ...   \n",
+       "1985563   addValue                                     ...   \n",
+       "331020    cat1                                         ...   \n",
+       "\n",
+       "                                                     4          5   \\\n",
+       "459259    1.0.0                                              29099   \n",
+       "1083589   1.0.0                                              29099   \n",
+       "252642    1.0.0                                              29099   \n",
+       "6821                                                        15230    \n",
+       "1229113   1.0.0                                              29099   \n",
+       "...                                                 ...        ...   \n",
+       "293631    1.0.0                                              29099   \n",
+       "431234    1.0.0                                              29099   \n",
+       "2299184                                                    1850165   \n",
+       "1985563   1.0.0                                            1187846   \n",
+       "331020    1.0.0                                              29099   \n",
+       "\n",
+       "                                                        6   \\\n",
+       "459259    cat1                                         ...   \n",
+       "1083589   cat1                                         ...   \n",
+       "252642    cat1                                         ...   \n",
+       "6821      toolshed.g2.bx.psu.edu/repos/devteam/fastqc/f...   \n",
+       "1229113   cat1                                         ...   \n",
+       "...                                                    ...   \n",
+       "293631    cat1                                         ...   \n",
+       "431234    cat1                                         ...   \n",
+       "2299184   toolshed.g2.bx.psu.edu/repos/iuc/purge_dups/p...   \n",
+       "1985563   toolshed.g2.bx.psu.edu/repos/bgruening/text_p...   \n",
+       "331020    cat1                                         ...   \n",
+       "\n",
+       "                                                     7            8   \\\n",
+       "459259    1.0.0                                           f            \n",
+       "1083589   1.0.0                                           f            \n",
+       "252642    1.0.0                                           f            \n",
+       "6821                                                      f            \n",
+       "1229113   1.0.0                                           f            \n",
+       "...                                                 ...          ...   \n",
+       "293631    1.0.0                                           f            \n",
+       "431234    1.0.0                                           f            \n",
+       "2299184   1.2.5+galaxy4                                   f            \n",
+       "1985563   0.1.0                                           f            \n",
+       "331020    1.0.0                                           f            \n",
+       "\n",
+       "                9   10  \n",
+       "459259    t          f  \n",
+       "1083589   t          f  \n",
+       "252642    t          f  \n",
+       "6821      t             \n",
+       "1229113   t          f  \n",
+       "...            ...  ..  \n",
+       "293631    t          f  \n",
+       "431234    t          f  \n",
+       "2299184   t          f  \n",
+       "1985563   t             \n",
+       "331020    t          f  \n",
+       "\n",
+       "[4999 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 56,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "wf_frame_subset = wf_frame_1[1:5000]\n",
+    "wf_frame_subset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "id": "69ae32d2-928b-4c1f-a059-338fa1d4e494",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "wf_frame_subset.to_csv(\"../data/wf_frame_subset_march_22_5000.csv\", index=None, header=None)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "cb300cf4-98c1-4eed-85c1-90763128513e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "wf_path_old = \"../data/worflow-connection-20-04.tsv\"\n",
+    "\n",
+    "wf_old = pd.read_csv(wf_path_old, sep=\"\\t\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "257c9f14-da19-4b4e-b09c-a08b85cc5f87",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>3</th>\n",
+       "      <th>2013-02-07 16:48:46.721866</th>\n",
+       "      <th>5</th>\n",
+       "      <th>Grep1</th>\n",
+       "      <th>1.0.1</th>\n",
+       "      <th>7</th>\n",
+       "      <th>Remove beginning1</th>\n",
+       "      <th>1.0.0</th>\n",
+       "      <th>f</th>\n",
+       "      <th>t</th>\n",
+       "      <th>f.1</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>3</td>\n",
+       "      <td>2013-02-07 16:48:46.721866</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Cut1</td>\n",
+       "      <td>1.0.1</td>\n",
+       "      <td>8</td>\n",
+       "      <td>addValue</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>3</td>\n",
+       "      <td>2013-02-07 16:48:46.721866</td>\n",
+       "      <td>7</td>\n",
+       "      <td>Remove beginning1</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>9</td>\n",
+       "      <td>Cut1</td>\n",
+       "      <td>1.0.1</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>2013-02-07 16:48:46.721866</td>\n",
+       "      <td>7</td>\n",
+       "      <td>Remove beginning1</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>6</td>\n",
+       "      <td>Cut1</td>\n",
+       "      <td>1.0.1</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3</td>\n",
+       "      <td>2013-02-07 16:48:46.721866</td>\n",
+       "      <td>8</td>\n",
+       "      <td>addValue</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>11</td>\n",
+       "      <td>Paste1</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>3</td>\n",
+       "      <td>2013-02-07 16:48:46.721866</td>\n",
+       "      <td>9</td>\n",
+       "      <td>Cut1</td>\n",
+       "      <td>1.0.1</td>\n",
+       "      <td>11</td>\n",
+       "      <td>Paste1</td>\n",
+       "      <td>1.0.0</td>\n",
+       "      <td>f</td>\n",
+       "      <td>t</td>\n",
+       "      <td>f</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>746133</th>\n",
+       "      <td>50779</td>\n",
+       "      <td>2020-04-27 14:36:39.197104</td>\n",
+       "      <td>727112</td>\n",
+       "      <td>Cut1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>727113</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/devteam/intersect...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>746134</th>\n",
+       "      <td>50779</td>\n",
+       "      <td>2020-04-27 14:36:39.197104</td>\n",
+       "      <td>727111</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/devteam/column_ma...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>727112</td>\n",
+       "      <td>Cut1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>746135</th>\n",
+       "      <td>50779</td>\n",
+       "      <td>2020-04-27 14:36:39.197104</td>\n",
+       "      <td>727110</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/devteam/column_ma...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>727111</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/devteam/column_ma...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>746136</th>\n",
+       "      <td>50779</td>\n",
+       "      <td>2020-04-27 14:36:39.197104</td>\n",
+       "      <td>727108</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>727114</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/devteam/intersect...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>746137</th>\n",
+       "      <td>50779</td>\n",
+       "      <td>2020-04-27 14:36:39.197104</td>\n",
+       "      <td>727108</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>727113</td>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/devteam/intersect...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>f</td>\n",
+       "      <td>f</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>746138 rows × 11 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "            3  2013-02-07 16:48:46.721866       5  \\\n",
+       "0           3  2013-02-07 16:48:46.721866       6   \n",
+       "1           3  2013-02-07 16:48:46.721866       7   \n",
+       "2           3  2013-02-07 16:48:46.721866       7   \n",
+       "3           3  2013-02-07 16:48:46.721866       8   \n",
+       "4           3  2013-02-07 16:48:46.721866       9   \n",
+       "...       ...                         ...     ...   \n",
+       "746133  50779  2020-04-27 14:36:39.197104  727112   \n",
+       "746134  50779  2020-04-27 14:36:39.197104  727111   \n",
+       "746135  50779  2020-04-27 14:36:39.197104  727110   \n",
+       "746136  50779  2020-04-27 14:36:39.197104  727108   \n",
+       "746137  50779  2020-04-27 14:36:39.197104  727108   \n",
+       "\n",
+       "                                                    Grep1  1.0.1       7  \\\n",
+       "0                                                    Cut1  1.0.1       8   \n",
+       "1                                       Remove beginning1  1.0.0       9   \n",
+       "2                                       Remove beginning1  1.0.0       6   \n",
+       "3                                                addValue  1.0.0      11   \n",
+       "4                                                    Cut1  1.0.1      11   \n",
+       "...                                                   ...    ...     ...   \n",
+       "746133                                               Cut1    NaN  727113   \n",
+       "746134  toolshed.g2.bx.psu.edu/repos/devteam/column_ma...    NaN  727112   \n",
+       "746135  toolshed.g2.bx.psu.edu/repos/devteam/column_ma...    NaN  727111   \n",
+       "746136                                                NaN    NaN  727114   \n",
+       "746137                                                NaN    NaN  727113   \n",
+       "\n",
+       "                                        Remove beginning1  1.0.0  f  t  f.1  \n",
+       "0                                                addValue  1.0.0  f  t    f  \n",
+       "1                                                    Cut1  1.0.1  f  t    f  \n",
+       "2                                                    Cut1  1.0.1  f  t    f  \n",
+       "3                                                  Paste1  1.0.0  f  t    f  \n",
+       "4                                                  Paste1  1.0.0  f  t    f  \n",
+       "...                                                   ...    ... .. ..  ...  \n",
+       "746133  toolshed.g2.bx.psu.edu/repos/devteam/intersect...    NaN  f  f  NaN  \n",
+       "746134                                               Cut1    NaN  f  f  NaN  \n",
+       "746135  toolshed.g2.bx.psu.edu/repos/devteam/column_ma...    NaN  f  f  NaN  \n",
+       "746136  toolshed.g2.bx.psu.edu/repos/devteam/intersect...    NaN  f  f  NaN  \n",
+       "746137  toolshed.g2.bx.psu.edu/repos/devteam/intersect...    NaN  f  f  NaN  \n",
+       "\n",
+       "[746138 rows x 11 columns]"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "wf_old"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "id": "821608ab-3b08-4ff3-99e1-6db5f04d3e05",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>0</th>\n",
+       "      <th>1</th>\n",
+       "      <th>2</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>...</td>\n",
+       "      <td>month</td>\n",
+       "      <td>count</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>----------------------------------------------...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/iuc/snpsift/snpS...</td>\n",
+       "      <td>2022-02-01</td>\n",
+       "      <td>67151</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/devteam/column_m...</td>\n",
+       "      <td>2022-02-01</td>\n",
+       "      <td>50054</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>upload1                                      ...</td>\n",
+       "      <td>2022-02-01</td>\n",
+       "      <td>43169</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27203</th>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/iuc/hmmer_jackhm...</td>\n",
+       "      <td>2021-02-01</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27204</th>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/galaxyp/openms_h...</td>\n",
+       "      <td>2021-02-01</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27205</th>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/iuc/circos/circo...</td>\n",
+       "      <td>2021-02-01</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27206</th>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/bgruening/chembl...</td>\n",
+       "      <td>2021-02-01</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27207</th>\n",
+       "      <td>(27205 rows)</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>27208 rows × 3 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                                       0             1  \\\n",
+       "0                                                    ...     month       \n",
+       "1      ----------------------------------------------...           NaN   \n",
+       "2       toolshed.g2.bx.psu.edu/repos/iuc/snpsift/snpS...   2022-02-01    \n",
+       "3       toolshed.g2.bx.psu.edu/repos/devteam/column_m...   2022-02-01    \n",
+       "4       upload1                                      ...   2022-02-01    \n",
+       "...                                                  ...           ...   \n",
+       "27203   toolshed.g2.bx.psu.edu/repos/iuc/hmmer_jackhm...   2021-02-01    \n",
+       "27204   toolshed.g2.bx.psu.edu/repos/galaxyp/openms_h...   2021-02-01    \n",
+       "27205   toolshed.g2.bx.psu.edu/repos/iuc/circos/circo...   2021-02-01    \n",
+       "27206   toolshed.g2.bx.psu.edu/repos/bgruening/chembl...   2021-02-01    \n",
+       "27207                                       (27205 rows)           NaN   \n",
+       "\n",
+       "              2  \n",
+       "0       count    \n",
+       "1           NaN  \n",
+       "2         67151  \n",
+       "3         50054  \n",
+       "4         43169  \n",
+       "...         ...  \n",
+       "27203         1  \n",
+       "27204         1  \n",
+       "27205         1  \n",
+       "27206         1  \n",
+       "27207       NaN  \n",
+       "\n",
+       "[27208 rows x 3 columns]"
+      ]
+     },
+     "execution_count": 61,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tool_popu_path = \"../data/tool-popularity_Feb_22_12.csv\"\n",
+    "tool_popu = pd.read_csv(tool_popu_path, sep=\"|\", header=None)\n",
+    "tool_popu"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "id": "b5330f2c-9533-40d6-9731-62edd9d950b0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>0</th>\n",
+       "      <th>1</th>\n",
+       "      <th>2</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/iuc/snpsift/snpS...</td>\n",
+       "      <td>2022-02-01</td>\n",
+       "      <td>67151</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/devteam/column_m...</td>\n",
+       "      <td>2022-02-01</td>\n",
+       "      <td>50054</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>upload1                                      ...</td>\n",
+       "      <td>2022-02-01</td>\n",
+       "      <td>43169</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/bgruening/text_p...</td>\n",
+       "      <td>2022-02-01</td>\n",
+       "      <td>39139</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>Cut1                                         ...</td>\n",
+       "      <td>2022-02-01</td>\n",
+       "      <td>29046</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27202</th>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/devteam/emboss_5...</td>\n",
+       "      <td>2021-02-01</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27203</th>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/iuc/hmmer_jackhm...</td>\n",
+       "      <td>2021-02-01</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27204</th>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/galaxyp/openms_h...</td>\n",
+       "      <td>2021-02-01</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27205</th>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/iuc/circos/circo...</td>\n",
+       "      <td>2021-02-01</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27206</th>\n",
+       "      <td>toolshed.g2.bx.psu.edu/repos/bgruening/chembl...</td>\n",
+       "      <td>2021-02-01</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>27205 rows × 3 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                                       0             1  \\\n",
+       "2       toolshed.g2.bx.psu.edu/repos/iuc/snpsift/snpS...   2022-02-01    \n",
+       "3       toolshed.g2.bx.psu.edu/repos/devteam/column_m...   2022-02-01    \n",
+       "4       upload1                                      ...   2022-02-01    \n",
+       "5       toolshed.g2.bx.psu.edu/repos/bgruening/text_p...   2022-02-01    \n",
+       "6       Cut1                                         ...   2022-02-01    \n",
+       "...                                                  ...           ...   \n",
+       "27202   toolshed.g2.bx.psu.edu/repos/devteam/emboss_5...   2021-02-01    \n",
+       "27203   toolshed.g2.bx.psu.edu/repos/iuc/hmmer_jackhm...   2021-02-01    \n",
+       "27204   toolshed.g2.bx.psu.edu/repos/galaxyp/openms_h...   2021-02-01    \n",
+       "27205   toolshed.g2.bx.psu.edu/repos/iuc/circos/circo...   2021-02-01    \n",
+       "27206   toolshed.g2.bx.psu.edu/repos/bgruening/chembl...   2021-02-01    \n",
+       "\n",
+       "             2  \n",
+       "2        67151  \n",
+       "3        50054  \n",
+       "4        43169  \n",
+       "5        39139  \n",
+       "6        29046  \n",
+       "...        ...  \n",
+       "27202        1  \n",
+       "27203        1  \n",
+       "27204        1  \n",
+       "27205        1  \n",
+       "27206        1  \n",
+       "\n",
+       "[27205 rows x 3 columns]"
+      ]
+     },
+     "execution_count": 62,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tool_popu_new = tool_popu[2:len(tool_popu.index) - 1]\n",
+    "tool_popu_new"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "id": "0fcd3329-30c2-4051-a3f1-6538ac9967eb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tool_popu_new.to_csv(\"../data/tool_popularity_march_22.csv\", index=None, header=None)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8bb00aa7-56c8-4913-a3e8-74a3cc505064",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.6.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}