-
-
Save alexander-wei/25db7389996deca9c562f699b1f48985 to your computer and use it in GitHub Desktop.
hacker news posts eda
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": 1, | |
"id": "7122056a-0dd2-47a7-8ed4-8747ea0f3fa4", | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"import numpy as np\n", | |
"import pandas as pd\n", | |
"from matplotlib import pyplot as plt\n", | |
"from sklearn.preprocessing import KBinsDiscretizer" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 2, | |
"id": "6a0e4caf-1bb0-43b2-ab3d-3cbbd3007411", | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"image/png": "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\n", | |
"text/plain": [ | |
"<Figure size 432x288 with 1 Axes>" | |
] | |
}, | |
"metadata": { | |
"needs_background": "light" | |
}, | |
"output_type": "display_data" | |
} | |
], | |
"source": [ | |
"_X = pd.read_csv(\"../archive/HN_posts_year_to_Sep_26_2016.csv\")\n", | |
"_X = _X.dropna()\n", | |
"all_times = list(_X['created_at'])\n", | |
"\n", | |
"Times = [sum(np.array([60,1]) * np.array(\\\n", | |
"[_.split('/') for _ in x.split(' ')][1][0].split(':')).astype(np.float64)\\\n", | |
") for x in all_times]\n", | |
"Times=np.array(Times);\n", | |
"\n", | |
"plt.hist(Times);" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 3, | |
"id": "2f1b7cc9-480b-427c-bb97-0fd5e599496a", | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"binme = KBinsDiscretizer(10,encode=\"ordinal\",strategy=\"uniform\")\n", | |
"\n", | |
"Times_ = binme.fit_transform(Times.reshape(-1,1))" | |
] | |
} | |
], | |
"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": "3.10.5" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 5 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment