Skip to content

Instantly share code, notes, and snippets.

@aborruso

aborruso/tidyDebby.ipynb

Last active February 8, 2018 19:15
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save aborruso/64673765b0bcac92c41120ff98c40c34 to your computer and use it in GitHub Desktop.
Save aborruso/64673765b0bcac92c41120ff98c40c34 to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
tidyDebby.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "tydyDebby.ipynb",
"version": "0.3.2",
"views": {},
"default_view": {},
"provenance": []
},
"kernelspec": {
"name": "python2",
"display_name": "Python 2"
}
},
"cells": [
{
"metadata": {
"id": "uJhfKWBlqy3W",
"colab_type": "code",
"colab": {
"autoexec": {
"startup": false,
"wait_interval": 0
}
}
},
"cell_type": "code",
"source": [
"import pandas as pd\n",
"url='https://rawgit.com/aborruso/093df8530cbc60c88f8ac4fb32f06b47/raw/fbafb7a3033e63686dbdee7d50fe43ea4918bc5a/data.csv'"
],
"execution_count": 0,
"outputs": []
},
{
"metadata": {
"id": "oxzyP3GRrUFG",
"colab_type": "code",
"colab": {
"autoexec": {
"startup": false,
"wait_interval": 0
}
}
},
"cell_type": "code",
"source": [
"df=pd.read_csv(url,header=None)"
],
"execution_count": 0,
"outputs": []
},
{
"metadata": {
"id": "0Y0uHr9Srg2S",
"colab_type": "code",
"colab": {
"autoexec": {
"startup": false,
"wait_interval": 0
},
"output_extras": [
{
"item_id": 1
}
],
"base_uri": "https://localhost:8080/",
"height": 175
},
"outputId": "73173783-6a2c-4873-dd49-56567d2726e3",
"executionInfo": {
"status": "ok",
"timestamp": 1518117277974,
"user_tz": -60,
"elapsed": 786,
"user": {
"displayName": "Andrea Borruso",
"photoUrl": "//lh4.googleusercontent.com/-RQTYEtcmSq8/AAAAAAAAAAI/AAAAAAAAgjw/xMY6SwF49C0/s50-c-k-no/photo.jpg",
"userId": "116128232873038517443"
}
}
},
"cell_type": "code",
"source": [
"df"
],
"execution_count": 45,
"outputs": [
{
"output_type": "execute_result",
"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",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Milano</td>\n",
" <td>a</td>\n",
" <td>Deborah</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Palermo</td>\n",
" <td>c</td>\n",
" <td>Aru</td>\n",
" <td>fg</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Torino</td>\n",
" <td>l</td>\n",
" <td>ci</td>\n",
" <td>po</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Cardiff</td>\n",
" <td>g</td>\n",
" <td>scrive</td>\n",
" <td>tt</td>\n",
" <td>l</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 0 1 2 3 4\n",
"0 Milano a Deborah NaN NaN\n",
"1 Palermo c Aru fg NaN\n",
"2 Torino l ci po NaN\n",
"3 Cardiff g scrive tt l"
]
},
"metadata": {
"tags": []
},
"execution_count": 45
}
]
},
{
"metadata": {
"id": "YDrgW87TtEbg",
"colab_type": "code",
"colab": {
"autoexec": {
"startup": false,
"wait_interval": 0
}
}
},
"cell_type": "code",
"source": [
"tydyDebby=df.melt(id_vars=[0],value_name='valori',var_name = 'colonna')"
],
"execution_count": 0,
"outputs": []
},
{
"metadata": {
"id": "EkMVg0WHyBsG",
"colab_type": "code",
"colab": {
"autoexec": {
"startup": false,
"wait_interval": 0
},
"output_extras": [
{
"item_id": 1
}
],
"base_uri": "https://localhost:8080/",
"height": 426
},
"outputId": "4bc4fc41-62da-4041-988b-be2aac77fe85",
"executionInfo": {
"status": "ok",
"timestamp": 1518117306721,
"user_tz": -60,
"elapsed": 728,
"user": {
"displayName": "Andrea Borruso",
"photoUrl": "//lh4.googleusercontent.com/-RQTYEtcmSq8/AAAAAAAAAAI/AAAAAAAAgjw/xMY6SwF49C0/s50-c-k-no/photo.jpg",
"userId": "116128232873038517443"
}
}
},
"cell_type": "code",
"source": [
"tydyDebby.rename(columns = {0:'nome'}, inplace=True)\n",
"tydyDebby.dropna(inplace=True,how='any')\n",
"tydyDebby"
],
"execution_count": 48,
"outputs": [
{
"output_type": "execute_result",
"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>nome</th>\n",
" <th>colonna</th>\n",
" <th>valori</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Milano</td>\n",
" <td>1</td>\n",
" <td>a</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Palermo</td>\n",
" <td>1</td>\n",
" <td>c</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Torino</td>\n",
" <td>1</td>\n",
" <td>l</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Cardiff</td>\n",
" <td>1</td>\n",
" <td>g</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Milano</td>\n",
" <td>2</td>\n",
" <td>Deborah</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>Palermo</td>\n",
" <td>2</td>\n",
" <td>Aru</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>Torino</td>\n",
" <td>2</td>\n",
" <td>ci</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>Cardiff</td>\n",
" <td>2</td>\n",
" <td>scrive</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>Palermo</td>\n",
" <td>3</td>\n",
" <td>fg</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>Torino</td>\n",
" <td>3</td>\n",
" <td>po</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>Cardiff</td>\n",
" <td>3</td>\n",
" <td>tt</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>Cardiff</td>\n",
" <td>4</td>\n",
" <td>l</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" nome colonna valori\n",
"0 Milano 1 a\n",
"1 Palermo 1 c\n",
"2 Torino 1 l\n",
"3 Cardiff 1 g\n",
"4 Milano 2 Deborah\n",
"5 Palermo 2 Aru\n",
"6 Torino 2 ci\n",
"7 Cardiff 2 scrive\n",
"9 Palermo 3 fg\n",
"10 Torino 3 po\n",
"11 Cardiff 3 tt\n",
"15 Cardiff 4 l"
]
},
"metadata": {
"tags": []
},
"execution_count": 48
}
]
},
{
"metadata": {
"id": "KNcxp6uPzTiQ",
"colab_type": "code",
"colab": {
"autoexec": {
"startup": false,
"wait_interval": 0
}
}
},
"cell_type": "code",
"source": [
""
],
"execution_count": 0,
"outputs": []
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment