100 lines
1.7 KiB
Plaintext
100 lines
1.7 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "2b3fface",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import pandas as pd"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "74f1f5ec",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"df= pd.read_parquet(\"cleaned_0000.parquet\")\n",
|
|
"print(df.shape)\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "05775454",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"df.head()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "99e17328",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"df.tail()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "0238d802",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"step2 = pd.read_parquet(\"output_windowed.parquet\")\n",
|
|
"step2.head()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "1257c535",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"step2.shape"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "3754c664",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Zeigt alle Kombinationen mit Häufigkeit\n",
|
|
"step2[['STUDY', 'LEVEL', 'PHASE']].value_counts()"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "base",
|
|
"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": "3.11.5"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|