scuti/stacksurvey
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Changed get_differences to result in a ratio.

Browse Source
This commit is contained in:
scuti
2025-04-20 06:07:55 -07:00
parent c6096cfe6c
commit 71d1efa292
1 changed files with 28 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
stackoverflow-survey.ipynb
View File

@@ -122,11 +122,14 @@
"# https://seaborn.pydata.org/examples/part_whole_bars.html\n",
"\n",
"# investigate extrinsic vs intrinsic motivation\n",
"def get_difference(dict1, dict2):\n",
"def get_difference(dict1, dict2, proportion=False):\n",
" keys = dict1.keys()\n",
" result = dict()\n",
" for key in keys:\n",
" result[key] = dict1[key] - dict2[key]\n",
" if proportion:\n",
" result[key] = round((dict1[key] - dict2[key])/dict2[key],2)\n",
" else:\n",
" result[key] = dict1[key] - dict2[key]\n",
" return result\n",
"\n",
"def visualize_diff(diff_dict, color=\"lightblue\", saveto=None):\n",
@@ -137,7 +140,6 @@
" df = pd.DataFrame(diff_sorted.items(), columns=['Languages', 'Value'])\n",
" plt.figure(figsize=(15,20)) \n",
" sb.barplot(x=KEY, y='Languages', data=df, color=color)\n",
" \n",
" DELTA = '\\u0394'\n",
" for index, value in enumerate(df[KEY]):\n",
" # chatgpt annotates my chart\n",
@@ -149,24 +151,33 @@
" # Adjust the x position for negative values\n",
" plt.text(value, index, DELTA+str(value), va='center', ha='right') \n",
" lowest = 0\n",
" offset = 0.5\n",
" offset = 0\n",
" positive_values = df[df[KEY] > 0][KEY]\n",
" if not positive_values.empty:\n",
" lowest = positive_values.min()\n",
" offset = list(positive_values).count(lowest) \n",
" if len(positive_values) < len(df):\n",
" # don't draw the line if every value is greater than 0\n",
" plt.axhline(y=df[KEY].tolist().index(lowest) + offset, color='red', linestyle='--')\n",
" # don't draw the line if every value is greater than 0_\n",
" plt.axhline(y=df[KEY].tolist().index(lowest) + (offset-0.5), \n",
" color='red', linestyle='--', zorder=-1)\n",
" if saveto is not None:\n",
" plt.savefig(saveto, bbox_inches='tight')\n",
" \n",
"motiv_diff = get_difference(l2, l1)\n",
"motiv_diff = get_difference(l2, l1, proportion=True)\n",
"# print(motiv_diff)\n",
"visualize_diff(motiv_diff, saveto=\"images/delta.png\")\n",
"motiv_diff = get_difference(l2, l1)\n",
"visualize_diff(motiv_diff, saveto=\"images/delta-b.png\")\n",
"\n",
"# no clear description of what \"admired\" is\n",
"# in the schema\n",
"# but generally people want to use the languages\n",
"# they admire\n",
"\n",
"# determine level of hype\n",
"hype = get_difference(l4, l3)\n",
"# hype = get_difference(l4, l3)\n",
"# print(hype)\n",
"visualize_diff(hype, color=\"red\")"
"# visualize_diff(hype, color=\"red\")"
]
},
{
@@ -263,6 +274,14 @@
"# earn less than the mean compensation\n",
"# (what titles have high standard deviations in earnings)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "acd193c3-eb73-498c-a8d4-c59c0eb5dcdb",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {