Skip to content
Permalink
b97b64ea62
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?

Dissertation/.ipynb_checkpoints/Final Code - SVM - No sampling - Drop Popping and Locking column-checkpoint.ipynb

Go to file
 
 
Cannot retrieve contributors at this time
2989 lines (2989 sloc) 383 KB
Raw Blame
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "3d1395e5",
"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>1. Consent: By clicking on the \"I Agree\" button below, you are indicating that you have read and understood the information provided above, that you voluntarily agree to participate in this study, and that you are at least 18 years of age.</th>\n",
" <th>2. I see Myself as Someone Who...</th>\n",
" <th>2.1. Is talkative</th>\n",
" <th>2.2. Tends to find fault with others</th>\n",
" <th>2.3. Does a thorough job</th>\n",
" <th>2.4. Is depressed, blue</th>\n",
" <th>2.5. Is original, comes up with new ideas</th>\n",
" <th>2.6. Is reserved</th>\n",
" <th>2.7. Is helpful and unselfish with others</th>\n",
" <th>2.8. Can be somewhat careless</th>\n",
" <th>...</th>\n",
" <th>2.36. Is outgoing, sociable</th>\n",
" <th>2.37. Is sometimes rude to others</th>\n",
" <th>2.38. Makes plans and follows through with them</th>\n",
" <th>2.39. Gets nervous easily</th>\n",
" <th>2.40. Likes to reflect, play with ideas</th>\n",
" <th>2.41. Has few artistic interests</th>\n",
" <th>2.42. Likes to cooperate with others</th>\n",
" <th>2.43. Is easily distracted</th>\n",
" <th>2.44. Is sophisticated in art, music, or literature</th>\n",
" <th>3. What is your favourite dance style in the context of dance battles from the ones in the list below:</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>I agree</td>\n",
" <td>NaN</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>House</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>I agree</td>\n",
" <td>NaN</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>Hip Hop</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>I agree</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>...</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>3.0</td>\n",
" <td>Dancehall</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>I agree</td>\n",
" <td>NaN</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>Dancehall</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>I agree</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>NaN</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>House</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",
" <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>83</th>\n",
" <td>I agree</td>\n",
" <td>NaN</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>Breaking</td>\n",
" </tr>\n",
" <tr>\n",
" <th>84</th>\n",
" <td>I agree</td>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>Hip Hop</td>\n",
" </tr>\n",
" <tr>\n",
" <th>85</th>\n",
" <td>I agree</td>\n",
" <td>NaN</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>5.0</td>\n",
" <td>Vogue</td>\n",
" </tr>\n",
" <tr>\n",
" <th>86</th>\n",
" <td>I agree</td>\n",
" <td>NaN</td>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>Hip Hop</td>\n",
" </tr>\n",
" <tr>\n",
" <th>87</th>\n",
" <td>I agree</td>\n",
" <td>NaN</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>Hip Hop</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>88 rows × 47 columns</p>\n",
"</div>"
],
"text/plain": [
" 1. Consent: By clicking on the \"I Agree\" button below, you are indicating that you have read and understood the information provided above, that you voluntarily agree to participate in this study, and that you are at least 18 years of age. \\\n",
"0 I agree \n",
"1 I agree \n",
"2 I agree \n",
"3 I agree \n",
"4 I agree \n",
".. ... \n",
"83 I agree \n",
"84 I agree \n",
"85 I agree \n",
"86 I agree \n",
"87 I agree \n",
"\n",
" 2. I see Myself as Someone Who... 2.1. Is talkative \\\n",
"0 NaN 4.0 \n",
"1 NaN 4.0 \n",
"2 NaN NaN \n",
"3 NaN 5.0 \n",
"4 NaN NaN \n",
".. ... ... \n",
"83 NaN 3.0 \n",
"84 NaN 1.0 \n",
"85 NaN 4.0 \n",
"86 NaN 5.0 \n",
"87 NaN 4.0 \n",
"\n",
" 2.2. Tends to find fault with others 2.3. Does a thorough job \\\n",
"0 2.0 3.0 \n",
"1 3.0 2.0 \n",
"2 NaN NaN \n",
"3 2.0 2.0 \n",
"4 1.0 3.0 \n",
".. ... ... \n",
"83 4.0 3.0 \n",
"84 2.0 3.0 \n",
"85 2.0 3.0 \n",
"86 3.0 4.0 \n",
"87 2.0 3.0 \n",
"\n",
" 2.4. Is depressed, blue 2.5. Is original, comes up with new ideas \\\n",
"0 3.0 2.0 \n",
"1 3.0 4.0 \n",
"2 NaN NaN \n",
"3 2.0 4.0 \n",
"4 NaN 3.0 \n",
".. ... ... \n",
"83 4.0 3.0 \n",
"84 4.0 2.0 \n",
"85 2.0 5.0 \n",
"86 4.0 4.0 \n",
"87 2.0 3.0 \n",
"\n",
" 2.6. Is reserved 2.7. Is helpful and unselfish with others \\\n",
"0 3.0 5.0 \n",
"1 4.0 5.0 \n",
"2 NaN NaN \n",
"3 2.0 4.0 \n",
"4 5.0 5.0 \n",
".. ... ... \n",
"83 2.0 4.0 \n",
"84 5.0 3.0 \n",
"85 2.0 5.0 \n",
"86 2.0 3.0 \n",
"87 2.0 4.0 \n",
"\n",
" 2.8. Can be somewhat careless ... 2.36. Is outgoing, sociable \\\n",
"0 2.0 ... 4.0 \n",
"1 4.0 ... 4.0 \n",
"2 NaN ... NaN \n",
"3 5.0 ... 5.0 \n",
"4 3.0 ... 3.0 \n",
".. ... ... ... \n",
"83 3.0 ... 4.0 \n",
"84 2.0 ... 1.0 \n",
"85 4.0 ... 4.0 \n",
"86 3.0 ... 5.0 \n",
"87 4.0 ... 4.0 \n",
"\n",
" 2.37. Is sometimes rude to others \\\n",
"0 3.0 \n",
"1 3.0 \n",
"2 NaN \n",
"3 3.0 \n",
"4 3.0 \n",
".. ... \n",
"83 2.0 \n",
"84 3.0 \n",
"85 3.0 \n",
"86 2.0 \n",
"87 2.0 \n",
"\n",
" 2.38. Makes plans and follows through with them \\\n",
"0 2.0 \n",
"1 3.0 \n",
"2 NaN \n",
"3 3.0 \n",
"4 3.0 \n",
".. ... \n",
"83 5.0 \n",
"84 2.0 \n",
"85 1.0 \n",
"86 3.0 \n",
"87 4.0 \n",
"\n",
" 2.39. Gets nervous easily 2.40. Likes to reflect, play with ideas \\\n",
"0 4.0 2.0 \n",
"1 4.0 4.0 \n",
"2 NaN NaN \n",
"3 1.0 3.0 \n",
"4 3.0 3.0 \n",
".. ... ... \n",
"83 4.0 4.0 \n",
"84 3.0 1.0 \n",
"85 1.0 4.0 \n",
"86 3.0 3.0 \n",
"87 2.0 2.0 \n",
"\n",
" 2.41. Has few artistic interests 2.42. Likes to cooperate with others \\\n",
"0 2.0 5.0 \n",
"1 4.0 4.0 \n",
"2 NaN NaN \n",
"3 1.0 4.0 \n",
"4 3.0 5.0 \n",
".. ... ... \n",
"83 3.0 4.0 \n",
"84 4.0 2.0 \n",
"85 5.0 4.0 \n",
"86 1.0 4.0 \n",
"87 3.0 3.0 \n",
"\n",
" 2.43. Is easily distracted \\\n",
"0 4.0 \n",
"1 4.0 \n",
"2 NaN \n",
"3 4.0 \n",
"4 3.0 \n",
".. ... \n",
"83 5.0 \n",
"84 1.0 \n",
"85 5.0 \n",
"86 3.0 \n",
"87 4.0 \n",
"\n",
" 2.44. Is sophisticated in art, music, or literature \\\n",
"0 3.0 \n",
"1 4.0 \n",
"2 3.0 \n",
"3 3.0 \n",
"4 2.0 \n",
".. ... \n",
"83 4.0 \n",
"84 1.0 \n",
"85 5.0 \n",
"86 5.0 \n",
"87 2.0 \n",
"\n",
" 3. What is your favourite dance style in the context of dance battles from the ones in the list below: \n",
"0 House \n",
"1 Hip Hop \n",
"2 Dancehall \n",
"3 Dancehall \n",
"4 House \n",
".. ... \n",
"83 Breaking \n",
"84 Hip Hop \n",
"85 Vogue \n",
"86 Hip Hop \n",
"87 Hip Hop \n",
"\n",
"[88 rows x 47 columns]"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\"\"\"\n",
"Importing libraries and the dataset.\n",
"Personality/Dance Prefferences Dataset\n",
"6 attributes: 5 predictor attributes and a target variable.\n",
"\"\"\"\n",
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"df = pd.read_csv('dataset.csv')\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "a1ab0d35",
"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>2.1. Is talkative</th>\n",
" <th>2.2. Tends to find fault with others</th>\n",
" <th>2.3. Does a thorough job</th>\n",
" <th>2.4. Is depressed, blue</th>\n",
" <th>2.5. Is original, comes up with new ideas</th>\n",
" <th>2.6. Is reserved</th>\n",
" <th>2.7. Is helpful and unselfish with others</th>\n",
" <th>2.8. Can be somewhat careless</th>\n",
" <th>2.9. Is relaxed, handles stress well</th>\n",
" <th>2.10. Is curious about many different things</th>\n",
" <th>...</th>\n",
" <th>2.36. Is outgoing, sociable</th>\n",
" <th>2.37. Is sometimes rude to others</th>\n",
" <th>2.38. Makes plans and follows through with them</th>\n",
" <th>2.39. Gets nervous easily</th>\n",
" <th>2.40. Likes to reflect, play with ideas</th>\n",
" <th>2.41. Has few artistic interests</th>\n",
" <th>2.42. Likes to cooperate with others</th>\n",
" <th>2.43. Is easily distracted</th>\n",
" <th>2.44. Is sophisticated in art, music, or literature</th>\n",
" <th>3. What is your favourite dance style in the context of dance battles from the ones in the list below:</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>House</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>Hip Hop</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\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",
" <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>3.0</td>\n",
" <td>Dancehall</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>Dancehall</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>NaN</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>House</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",
" <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>83</th>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>Breaking</td>\n",
" </tr>\n",
" <tr>\n",
" <th>84</th>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>...</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>Hip Hop</td>\n",
" </tr>\n",
" <tr>\n",
" <th>85</th>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>5.0</td>\n",
" <td>Vogue</td>\n",
" </tr>\n",
" <tr>\n",
" <th>86</th>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>Hip Hop</td>\n",
" </tr>\n",
" <tr>\n",
" <th>87</th>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>Hip Hop</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>88 rows × 45 columns</p>\n",
"</div>"
],
"text/plain": [
" 2.1. Is talkative 2.2. Tends to find fault with others \\\n",
"0 4.0 2.0 \n",
"1 4.0 3.0 \n",
"2 NaN NaN \n",
"3 5.0 2.0 \n",
"4 NaN 1.0 \n",
".. ... ... \n",
"83 3.0 4.0 \n",
"84 1.0 2.0 \n",
"85 4.0 2.0 \n",
"86 5.0 3.0 \n",
"87 4.0 2.0 \n",
"\n",
" 2.3. Does a thorough job 2.4. Is depressed, blue \\\n",
"0 3.0 3.0 \n",
"1 2.0 3.0 \n",
"2 NaN NaN \n",
"3 2.0 2.0 \n",
"4 3.0 NaN \n",
".. ... ... \n",
"83 3.0 4.0 \n",
"84 3.0 4.0 \n",
"85 3.0 2.0 \n",
"86 4.0 4.0 \n",
"87 3.0 2.0 \n",
"\n",
" 2.5. Is original, comes up with new ideas 2.6. Is reserved \\\n",
"0 2.0 3.0 \n",
"1 4.0 4.0 \n",
"2 NaN NaN \n",
"3 4.0 2.0 \n",
"4 3.0 5.0 \n",
".. ... ... \n",
"83 3.0 2.0 \n",
"84 2.0 5.0 \n",
"85 5.0 2.0 \n",
"86 4.0 2.0 \n",
"87 3.0 2.0 \n",
"\n",
" 2.7. Is helpful and unselfish with others 2.8. Can be somewhat careless \\\n",
"0 5.0 2.0 \n",
"1 5.0 4.0 \n",
"2 NaN NaN \n",
"3 4.0 5.0 \n",
"4 5.0 3.0 \n",
".. ... ... \n",
"83 4.0 3.0 \n",
"84 3.0 2.0 \n",
"85 5.0 4.0 \n",
"86 3.0 3.0 \n",
"87 4.0 4.0 \n",
"\n",
" 2.9. Is relaxed, handles stress well \\\n",
"0 1.0 \n",
"1 3.0 \n",
"2 NaN \n",
"3 4.0 \n",
"4 3.0 \n",
".. ... \n",
"83 1.0 \n",
"84 5.0 \n",
"85 3.0 \n",
"86 3.0 \n",
"87 3.0 \n",
"\n",
" 2.10. Is curious about many different things ... \\\n",
"0 4.0 ... \n",
"1 4.0 ... \n",
"2 NaN ... \n",
"3 5.0 ... \n",
"4 5.0 ... \n",
".. ... ... \n",
"83 5.0 ... \n",
"84 2.0 ... \n",
"85 5.0 ... \n",
"86 4.0 ... \n",
"87 3.0 ... \n",
"\n",
" 2.36. Is outgoing, sociable 2.37. Is sometimes rude to others \\\n",
"0 4.0 3.0 \n",
"1 4.0 3.0 \n",
"2 NaN NaN \n",
"3 5.0 3.0 \n",
"4 3.0 3.0 \n",
".. ... ... \n",
"83 4.0 2.0 \n",
"84 1.0 3.0 \n",
"85 4.0 3.0 \n",
"86 5.0 2.0 \n",
"87 4.0 2.0 \n",
"\n",
" 2.38. Makes plans and follows through with them \\\n",
"0 2.0 \n",
"1 3.0 \n",
"2 NaN \n",
"3 3.0 \n",
"4 3.0 \n",
".. ... \n",
"83 5.0 \n",
"84 2.0 \n",
"85 1.0 \n",
"86 3.0 \n",
"87 4.0 \n",
"\n",
" 2.39. Gets nervous easily 2.40. Likes to reflect, play with ideas \\\n",
"0 4.0 2.0 \n",
"1 4.0 4.0 \n",
"2 NaN NaN \n",
"3 1.0 3.0 \n",
"4 3.0 3.0 \n",
".. ... ... \n",
"83 4.0 4.0 \n",
"84 3.0 1.0 \n",
"85 1.0 4.0 \n",
"86 3.0 3.0 \n",
"87 2.0 2.0 \n",
"\n",
" 2.41. Has few artistic interests 2.42. Likes to cooperate with others \\\n",
"0 2.0 5.0 \n",
"1 4.0 4.0 \n",
"2 NaN NaN \n",
"3 1.0 4.0 \n",
"4 3.0 5.0 \n",
".. ... ... \n",
"83 3.0 4.0 \n",
"84 4.0 2.0 \n",
"85 5.0 4.0 \n",
"86 1.0 4.0 \n",
"87 3.0 3.0 \n",
"\n",
" 2.43. Is easily distracted \\\n",
"0 4.0 \n",
"1 4.0 \n",
"2 NaN \n",
"3 4.0 \n",
"4 3.0 \n",
".. ... \n",
"83 5.0 \n",
"84 1.0 \n",
"85 5.0 \n",
"86 3.0 \n",
"87 4.0 \n",
"\n",
" 2.44. Is sophisticated in art, music, or literature \\\n",
"0 3.0 \n",
"1 4.0 \n",
"2 3.0 \n",
"3 3.0 \n",
"4 2.0 \n",
".. ... \n",
"83 4.0 \n",
"84 1.0 \n",
"85 5.0 \n",
"86 5.0 \n",
"87 2.0 \n",
"\n",
" 3. What is your favourite dance style in the context of dance battles from the ones in the list below: \n",
"0 House \n",
"1 Hip Hop \n",
"2 Dancehall \n",
"3 Dancehall \n",
"4 House \n",
".. ... \n",
"83 Breaking \n",
"84 Hip Hop \n",
"85 Vogue \n",
"86 Hip Hop \n",
"87 Hip Hop \n",
"\n",
"[88 rows x 45 columns]"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\"\"\"\n",
"In this section the data is being preproccesed (cleaned)\n",
"\n",
"\"\"\"\n",
"# drop the first two columns as they are not part of the actual dataset to be analysed\n",
"df = df.iloc[:, 2:]\n",
"\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "e9f6a20f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"2 43\n",
"4 2\n",
"5 1\n",
"17 1\n",
"18 2\n",
"20 13\n",
"22 1\n",
"24 1\n",
"29 1\n",
"31 1\n",
"33 1\n",
"34 11\n",
"41 1\n",
"47 3\n",
"53 2\n",
"59 2\n",
"66 43\n",
"67 1\n",
"73 1\n",
"76 1\n",
"81 1\n",
"dtype: int64"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\"\"\"\n",
"SECTION 1: MISSING VALUES\n",
"NaN values affect the model accuracy and sampling\n",
"\"\"\"\n",
"# count the number of null values for each row\n",
"null_counts = df[df.isnull().any(axis=1)].isnull().sum(axis=1)\n",
"null_counts"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "d61dc0ab",
"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>2.1. Is talkative</th>\n",
" <th>2.2. Tends to find fault with others</th>\n",
" <th>2.3. Does a thorough job</th>\n",
" <th>2.4. Is depressed, blue</th>\n",
" <th>2.5. Is original, comes up with new ideas</th>\n",
" <th>2.6. Is reserved</th>\n",
" <th>2.7. Is helpful and unselfish with others</th>\n",
" <th>2.8. Can be somewhat careless</th>\n",
" <th>2.9. Is relaxed, handles stress well</th>\n",
" <th>2.10. Is curious about many different things</th>\n",
" <th>...</th>\n",
" <th>2.36. Is outgoing, sociable</th>\n",
" <th>2.37. Is sometimes rude to others</th>\n",
" <th>2.38. Makes plans and follows through with them</th>\n",
" <th>2.39. Gets nervous easily</th>\n",
" <th>2.40. Likes to reflect, play with ideas</th>\n",
" <th>2.41. Has few artistic interests</th>\n",
" <th>2.42. Likes to cooperate with others</th>\n",
" <th>2.43. Is easily distracted</th>\n",
" <th>2.44. Is sophisticated in art, music, or literature</th>\n",
" <th>3. What is your favourite dance style in the context of dance battles from the ones in the list below:</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>1.0</td>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>...</td>\n",
" <td>1.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>Popping</td>\n",
" </tr>\n",
" <tr>\n",
" <th>34</th>\n",
" <td>1.0</td>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>...</td>\n",
" <td>1.0</td>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>NaN</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>Popping</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>2 rows × 45 columns</p>\n",
"</div>"
],
"text/plain": [
" 2.1. Is talkative 2.2. Tends to find fault with others \\\n",
"20 1.0 NaN \n",
"34 1.0 NaN \n",
"\n",
" 2.3. Does a thorough job 2.4. Is depressed, blue \\\n",
"20 1.0 NaN \n",
"34 1.0 NaN \n",
"\n",
" 2.5. Is original, comes up with new ideas 2.6. Is reserved \\\n",
"20 1.0 NaN \n",
"34 1.0 NaN \n",
"\n",
" 2.7. Is helpful and unselfish with others 2.8. Can be somewhat careless \\\n",
"20 1.0 NaN \n",
"34 1.0 NaN \n",
"\n",
" 2.9. Is relaxed, handles stress well \\\n",
"20 1.0 \n",
"34 1.0 \n",
"\n",
" 2.10. Is curious about many different things ... \\\n",
"20 1.0 ... \n",
"34 1.0 ... \n",
"\n",
" 2.36. Is outgoing, sociable 2.37. Is sometimes rude to others \\\n",
"20 1.0 NaN \n",
"34 1.0 NaN \n",
"\n",
" 2.38. Makes plans and follows through with them \\\n",
"20 NaN \n",
"34 1.0 \n",
"\n",
" 2.39. Gets nervous easily 2.40. Likes to reflect, play with ideas \\\n",
"20 1.0 1.0 \n",
"34 1.0 1.0 \n",
"\n",
" 2.41. Has few artistic interests 2.42. Likes to cooperate with others \\\n",
"20 1.0 1.0 \n",
"34 NaN 1.0 \n",
"\n",
" 2.43. Is easily distracted \\\n",
"20 1.0 \n",
"34 1.0 \n",
"\n",
" 2.44. Is sophisticated in art, music, or literature \\\n",
"20 1.0 \n",
"34 1.0 \n",
"\n",
" 3. What is your favourite dance style in the context of dance battles from the ones in the list below: \n",
"20 Popping \n",
"34 Popping \n",
"\n",
"[2 rows x 45 columns]"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# display rows with indices 20 and 34 to inspect as they have many NaN values\n",
"\n",
"rows_to_display = [20, 34]\n",
"df_display = df.iloc[rows_to_display]\n",
"\n",
"df_display"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "15902c3b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"4 2\n",
"5 1\n",
"17 1\n",
"18 2\n",
"22 1\n",
"24 1\n",
"29 1\n",
"31 1\n",
"33 1\n",
"41 1\n",
"47 3\n",
"53 2\n",
"59 2\n",
"67 1\n",
"73 1\n",
"76 1\n",
"81 1\n",
"dtype: int64"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# drop rows with index labels 2 and 66 as they have 43out of 44 NaN\n",
"#drop rows 20 and 34 as they seem to be faulty (25% NaN and all the other values = 1.0)\n",
"df = df.drop([2, 66, 20, 34], axis=0)\n",
"\n",
"# recount the number of null values for verification\n",
"null_counts = df[df.isnull().any(axis=1)].isnull().sum(axis=1)\n",
"null_counts\n"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "51881feb",
"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>2.1. Is talkative</th>\n",
" <th>2.2. Tends to find fault with others</th>\n",
" <th>2.3. Does a thorough job</th>\n",
" <th>2.4. Is depressed, blue</th>\n",
" <th>2.5. Is original, comes up with new ideas</th>\n",
" <th>2.6. Is reserved</th>\n",
" <th>2.7. Is helpful and unselfish with others</th>\n",
" <th>2.8. Can be somewhat careless</th>\n",
" <th>2.9. Is relaxed, handles stress well</th>\n",
" <th>2.10. Is curious about many different things</th>\n",
" <th>...</th>\n",
" <th>2.36. Is outgoing, sociable</th>\n",
" <th>2.37. Is sometimes rude to others</th>\n",
" <th>2.38. Makes plans and follows through with them</th>\n",
" <th>2.39. Gets nervous easily</th>\n",
" <th>2.40. Likes to reflect, play with ideas</th>\n",
" <th>2.41. Has few artistic interests</th>\n",
" <th>2.42. Likes to cooperate with others</th>\n",
" <th>2.43. Is easily distracted</th>\n",
" <th>2.44. Is sophisticated in art, music, or literature</th>\n",
" <th>3. What is your favourite dance style in the context of dance battles from the ones in the list below:</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>House</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>...</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>Hip Hop</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>2.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>4.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>Dancehall</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>0.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>House</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>5.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>3.0</td>\n",
" <td>4.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>...</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>3.0</td>\n",
" <td>5.0</td>\n",
" <td>Hip Hop</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 45 columns</p>\n",
"</div>"
],
"text/plain": [
" 2.1. Is talkative 2.2. Tends to find fault with others \\\n",
"0 4.0 2.0 \n",
"1 4.0 3.0 \n",
"3 5.0 2.0 \n",
"4 0.0 1.0 \n",
"5 1.0 1.0 \n",
"\n",
" 2.3. Does a thorough job 2.4. Is depressed, blue \\\n",
"0 3.0 3.0 \n",
"1 2.0 3.0 \n",
"3 2.0 2.0 \n",
"4 3.0 0.0 \n",
"5 5.0 1.0 \n",
"\n",
" 2.5. Is original, comes up with new ideas 2.6. Is reserved \\\n",
"0 2.0 3.0 \n",
"1 4.0 4.0 \n",
"3 4.0 2.0 \n",
"4 3.0 5.0 \n",
"5 3.0 5.0 \n",
"\n",
" 2.7. Is helpful and unselfish with others 2.8. Can be somewhat careless \\\n",
"0 5.0 2.0 \n",
"1 5.0 4.0 \n",
"3 4.0 5.0 \n",
"4 5.0 3.0 \n",
"5 3.0 4.0 \n",
"\n",
" 2.9. Is relaxed, handles stress well \\\n",
"0 1.0 \n",
"1 3.0 \n",
"3 4.0 \n",
"4 3.0 \n",
"5 3.0 \n",
"\n",
" 2.10. Is curious about many different things ... \\\n",
"0 4.0 ... \n",
"1 4.0 ... \n",
"3 5.0 ... \n",
"4 5.0 ... \n",
"5 5.0 ... \n",
"\n",
" 2.36. Is outgoing, sociable 2.37. Is sometimes rude to others \\\n",
"0 4.0 3.0 \n",
"1 4.0 3.0 \n",
"3 5.0 3.0 \n",
"4 3.0 3.0 \n",
"5 4.0 1.0 \n",
"\n",
" 2.38. Makes plans and follows through with them 2.39. Gets nervous easily \\\n",
"0 2.0 4.0 \n",
"1 3.0 4.0 \n",
"3 3.0 1.0 \n",
"4 3.0 3.0 \n",
"5 4.0 4.0 \n",
"\n",
" 2.40. Likes to reflect, play with ideas 2.41. Has few artistic interests \\\n",
"0 2.0 2.0 \n",
"1 4.0 4.0 \n",
"3 3.0 1.0 \n",
"4 3.0 3.0 \n",
"5 4.0 1.0 \n",
"\n",
" 2.42. Likes to cooperate with others 2.43. Is easily distracted \\\n",
"0 5.0 4.0 \n",
"1 4.0 4.0 \n",
"3 4.0 4.0 \n",
"4 5.0 3.0 \n",
"5 3.0 3.0 \n",
"\n",
" 2.44. Is sophisticated in art, music, or literature \\\n",
"0 3.0 \n",
"1 4.0 \n",
"3 3.0 \n",
"4 2.0 \n",
"5 5.0 \n",
"\n",
" 3. What is your favourite dance style in the context of dance battles from the ones in the list below: \n",
"0 House \n",
"1 Hip Hop \n",
"3 Dancehall \n",
"4 House \n",
"5 Hip Hop \n",
"\n",
"[5 rows x 45 columns]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\"\"\"\n",
"The oher NaN values will not affect the results considerabily\n",
"Approach: will not be taken in consideration when calculating personality indexes as they are all below 3/44 NaN records each.\n",
"The formula that needs to be applied according to Personality-BigFiveInventory is a simple addition, so the NaN should be replaced by 0 in order to stay neutral.\n",
"\"\"\"\n",
"\n",
"df.fillna(value=0.0, inplace=True)\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "a0b307e9",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\DellG3\\AppData\\Local\\Temp\\ipykernel_15844\\3029970098.py:23: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError. Select only valid columns before calling the reduction.\n",
" 'Openness': df.iloc[:, openness_cols].sum(axis=1),\n"
]
},
{
"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>Extraversion</th>\n",
" <th>Agreeableness</th>\n",
" <th>Conscientiousness</th>\n",
" <th>Neuroticism</th>\n",
" <th>Openness</th>\n",
" <th>Dance_Style</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>27.0</td>\n",
" <td>30.0</td>\n",
" <td>29.0</td>\n",
" <td>27.0</td>\n",
" <td>32.0</td>\n",
" <td>House</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>32.0</td>\n",
" <td>31.0</td>\n",
" <td>33.0</td>\n",
" <td>34.0</td>\n",
" <td>37.0</td>\n",
" <td>Hip Hop</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>26.0</td>\n",
" <td>30.0</td>\n",
" <td>24.0</td>\n",
" <td>29.0</td>\n",
" <td>30.0</td>\n",
" <td>Dancehall</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>22.0</td>\n",
" <td>26.0</td>\n",
" <td>18.0</td>\n",
" <td>24.0</td>\n",
" <td>33.0</td>\n",
" <td>House</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>22.0</td>\n",
" <td>34.0</td>\n",
" <td>27.0</td>\n",
" <td>31.0</td>\n",
" <td>31.0</td>\n",
" <td>Hip Hop</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Extraversion Agreeableness Conscientiousness Neuroticism Openness \\\n",
"0 27.0 30.0 29.0 27.0 32.0 \n",
"1 32.0 31.0 33.0 34.0 37.0 \n",
"3 26.0 30.0 24.0 29.0 30.0 \n",
"4 22.0 26.0 18.0 24.0 33.0 \n",
"5 22.0 34.0 27.0 31.0 31.0 \n",
"\n",
" Dance_Style \n",
"0 House \n",
"1 Hip Hop \n",
"3 Dancehall \n",
"4 House \n",
"5 Hip Hop "
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\"\"\"\n",
"SECTION 2: FORMULA\n",
"Extraversion: 1, 6R, 11, 16, 21R, 26, 31R, 36 \n",
"Agreeableness: 2R, 7, 12R, 17, 22, 27R, 32, 37R, 42 \n",
"Conscientiousness: 3, 8R, 13, 18R, 23R, 28, 33, 38, 43R \n",
"Neuroticism: 4, 9R, 14, 19, 24R, 29, 34R, 39 \n",
"Openness: 5, 10, 15, 20, 25, 30, 35R, 40, 41R, 44\n",
"\n",
"\"\"\"\n",
"# Define the column groups\n",
"extraversion_cols = [1, 6, 11, 16, 21, 26, 31, 36]\n",
"agreeableness_cols = [2, 7, 12, 17, 22, 27, 32, 37, 42]\n",
"conscientiousness_cols = [3, 8, 13, 18, 23, 28, 33, 38, 43]\n",
"neuroticism_cols = [4, 9, 14, 19, 24, 29, 34, 39]\n",
"openness_cols = [5, 10, 15, 20, 25, 30, 35, 40, 41, 44]\n",
"\n",
"# Create a new DataFrame with the sum of the specified columns for each category\n",
"category_df = pd.DataFrame({\n",
" 'Extraversion': df.iloc[:, extraversion_cols].sum(axis=1),\n",
" 'Agreeableness': df.iloc[:, agreeableness_cols].sum(axis=1),\n",
" 'Conscientiousness': df.iloc[:, conscientiousness_cols].sum(axis=1),\n",
" 'Neuroticism': df.iloc[:, neuroticism_cols].sum(axis=1),\n",
" 'Openness': df.iloc[:, openness_cols].sum(axis=1),\n",
" 'Dance_Style': df.iloc[:,-1]\n",
"})\n",
"\n",
"category_df.head()\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "582781d4",
"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>Extraversion</th>\n",
" <th>Agreeableness</th>\n",
" <th>Conscientiousness</th>\n",
" <th>Neuroticism</th>\n",
" <th>Openness</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.193076</td>\n",
" <td>-0.258444</td>\n",
" <td>-0.031753</td>\n",
" <td>-0.976851</td>\n",
" <td>0.068336</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.403400</td>\n",
" <td>-0.034637</td>\n",
" <td>0.857323</td>\n",
" <td>0.441392</td>\n",
" <td>1.093373</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>-0.048989</td>\n",
" <td>-0.258444</td>\n",
" <td>-1.143097</td>\n",
" <td>-0.571639</td>\n",
" <td>-0.341679</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>-1.017249</td>\n",
" <td>-1.153674</td>\n",
" <td>-2.476711</td>\n",
" <td>-1.584670</td>\n",
" <td>0.273343</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>-1.017249</td>\n",
" <td>0.636786</td>\n",
" <td>-0.476290</td>\n",
" <td>-0.166427</td>\n",
" <td>-0.136672</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>79</th>\n",
" <td>0.435140</td>\n",
" <td>1.532016</td>\n",
" <td>0.857323</td>\n",
" <td>-0.369033</td>\n",
" <td>0.068336</td>\n",
" </tr>\n",
" <tr>\n",
" <th>80</th>\n",
" <td>-1.501379</td>\n",
" <td>-2.496519</td>\n",
" <td>-0.698559</td>\n",
" <td>-3.610732</td>\n",
" <td>-1.161708</td>\n",
" </tr>\n",
" <tr>\n",
" <th>81</th>\n",
" <td>0.677205</td>\n",
" <td>0.189171</td>\n",
" <td>0.635054</td>\n",
" <td>0.441392</td>\n",
" <td>-0.341679</td>\n",
" </tr>\n",
" <tr>\n",
" <th>82</th>\n",
" <td>-0.775184</td>\n",
" <td>-0.482252</td>\n",
" <td>1.079592</td>\n",
" <td>-0.774245</td>\n",
" <td>-0.341679</td>\n",
" </tr>\n",
" <tr>\n",
" <th>83</th>\n",
" <td>-1.501379</td>\n",
" <td>0.189171</td>\n",
" <td>-0.698559</td>\n",
" <td>-1.787276</td>\n",
" <td>-1.161708</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>84 rows × 5 columns</p>\n",
"</div>"
],
"text/plain": [
" Extraversion Agreeableness Conscientiousness Neuroticism Openness\n",
"0 0.193076 -0.258444 -0.031753 -0.976851 0.068336\n",
"1 1.403400 -0.034637 0.857323 0.441392 1.093373\n",
"2 -0.048989 -0.258444 -1.143097 -0.571639 -0.341679\n",
"3 -1.017249 -1.153674 -2.476711 -1.584670 0.273343\n",
"4 -1.017249 0.636786 -0.476290 -0.166427 -0.136672\n",
".. ... ... ... ... ...\n",
"79 0.435140 1.532016 0.857323 -0.369033 0.068336\n",
"80 -1.501379 -2.496519 -0.698559 -3.610732 -1.161708\n",
"81 0.677205 0.189171 0.635054 0.441392 -0.341679\n",
"82 -0.775184 -0.482252 1.079592 -0.774245 -0.341679\n",
"83 -1.501379 0.189171 -0.698559 -1.787276 -1.161708\n",
"\n",
"[84 rows x 5 columns]"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\"\"\"\n",
"SECTION 3: Scaling the numerical features using StandardScaler\n",
"\"\"\"\n",
"X = category_df.loc[:, category_df.columns != 'Dance_Style'] # select all columns except target\n",
"y = category_df['Dance_Style'] # select only the target column\n",
"\n",
"from sklearn.preprocessing import StandardScaler\n",
"\n",
"scaler = StandardScaler()\n",
"X_scaled = scaler.fit_transform(X)\n",
"\n",
"column_names =['Extraversion','Agreeableness','Conscientiousness','Neuroticism','Openness']\n",
"df_scaled = pd.DataFrame(X_scaled, columns=column_names)\n",
"df_scaled "
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "3e95c3e5",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"\"\"\"\n",
"SECION 4: Encoding the target variable\n",
"\"\"\"\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"target_counts = y.value_counts()\n",
"sns.barplot(x=target_counts.index, y=target_counts.values)\n",
"plt.title('Class Distribution of Dance Styles')\n",
"plt.xlabel('Dance Styles')\n",
"plt.ylabel('Count')\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "13d6abf5",
"metadata": {},
"outputs": [],
"source": [
"#combining Locking and Popping\n",
"y= y.replace({'Popping': 'Popping/Locking', 'Locking': 'Popping/Locking'})"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "533107a2",
"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>Breaking</th>\n",
" <th>Dancehall</th>\n",
" <th>Hip Hop</th>\n",
" <th>House</th>\n",
" <th>Popping/Locking</th>\n",
" <th>Vogue</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</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",
" </tr>\n",
" <tr>\n",
" <th>83</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>84</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>85</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>86</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>87</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>84 rows × 6 columns</p>\n",
"</div>"
],
"text/plain": [
" Breaking Dancehall Hip Hop House Popping/Locking Vogue\n",
"0 0 0 0 1 0 0\n",
"1 0 0 1 0 0 0\n",
"3 0 1 0 0 0 0\n",
"4 0 0 0 1 0 0\n",
"5 0 0 1 0 0 0\n",
".. ... ... ... ... ... ...\n",
"83 1 0 0 0 0 0\n",
"84 0 0 1 0 0 0\n",
"85 0 0 0 0 0 1\n",
"86 0 0 1 0 0 0\n",
"87 0 0 1 0 0 0\n",
"\n",
"[84 rows x 6 columns]"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#encoding the target text variables using One Hot Encoder \n",
"df_encoded = pd.get_dummies(y)\n",
"df_encoded"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "e1e72352",
"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>Breaking</th>\n",
" <th>Dancehall</th>\n",
" <th>Hip Hop</th>\n",
" <th>House</th>\n",
" <th>Popping/Locking</th>\n",
" <th>Vogue</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</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",
" </tr>\n",
" <tr>\n",
" <th>79</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>80</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>81</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>82</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>83</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>84 rows × 6 columns</p>\n",
"</div>"
],
"text/plain": [
" Breaking Dancehall Hip Hop House Popping/Locking Vogue\n",
"0 0 0 0 1 0 0\n",
"1 0 0 1 0 0 0\n",
"2 0 1 0 0 0 0\n",
"3 0 0 0 1 0 0\n",
"4 0 0 1 0 0 0\n",
".. ... ... ... ... ... ...\n",
"79 1 0 0 0 0 0\n",
"80 0 0 1 0 0 0\n",
"81 0 0 0 0 0 1\n",
"82 0 0 1 0 0 0\n",
"83 0 0 1 0 0 0\n",
"\n",
"[84 rows x 6 columns]"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#reset the index that was originally affected by the dropped columns\n",
"df_encoded = df_encoded.reset_index(drop=True)\n",
"df_encoded"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "518cc734",
"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>Breaking</th>\n",
" <th>Dancehall</th>\n",
" <th>Hip Hop</th>\n",
" <th>House</th>\n",
" <th>Vogue</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>79</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>80</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>81</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>82</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>83</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>84 rows × 5 columns</p>\n",
"</div>"
],
"text/plain": [
" Breaking Dancehall Hip Hop House Vogue\n",
"0 0 0 0 1 0\n",
"1 0 0 1 0 0\n",
"2 0 1 0 0 0\n",
"3 0 0 0 1 0\n",
"4 0 0 1 0 0\n",
".. ... ... ... ... ...\n",
"79 1 0 0 0 0\n",
"80 0 0 1 0 0\n",
"81 0 0 0 0 1\n",
"82 0 0 1 0 0\n",
"83 0 0 1 0 0\n",
"\n",
"[84 rows x 5 columns]"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_encoded = df_encoded.drop('Popping/Locking', axis=1 )\n",
"df_encoded"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "abaa125f",
"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>Extraversion</th>\n",
" <th>Agreeableness</th>\n",
" <th>Conscientiousness</th>\n",
" <th>Neuroticism</th>\n",
" <th>Openness</th>\n",
" <th>Breaking</th>\n",
" <th>Dancehall</th>\n",
" <th>Hip Hop</th>\n",
" <th>House</th>\n",
" <th>Vogue</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.193076</td>\n",
" <td>-0.258444</td>\n",
" <td>-0.031753</td>\n",
" <td>-0.976851</td>\n",
" <td>0.068336</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.403400</td>\n",
" <td>-0.034637</td>\n",
" <td>0.857323</td>\n",
" <td>0.441392</td>\n",
" <td>1.093373</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>-0.048989</td>\n",
" <td>-0.258444</td>\n",
" <td>-1.143097</td>\n",
" <td>-0.571639</td>\n",
" <td>-0.341679</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>-1.017249</td>\n",
" <td>-1.153674</td>\n",
" <td>-2.476711</td>\n",
" <td>-1.584670</td>\n",
" <td>0.273343</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>-1.017249</td>\n",
" <td>0.636786</td>\n",
" <td>-0.476290</td>\n",
" <td>-0.166427</td>\n",
" <td>-0.136672</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</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",
" </tr>\n",
" <tr>\n",
" <th>79</th>\n",
" <td>0.435140</td>\n",
" <td>1.532016</td>\n",
" <td>0.857323</td>\n",
" <td>-0.369033</td>\n",
" <td>0.068336</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>80</th>\n",
" <td>-1.501379</td>\n",
" <td>-2.496519</td>\n",
" <td>-0.698559</td>\n",
" <td>-3.610732</td>\n",
" <td>-1.161708</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>81</th>\n",
" <td>0.677205</td>\n",
" <td>0.189171</td>\n",
" <td>0.635054</td>\n",
" <td>0.441392</td>\n",
" <td>-0.341679</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>82</th>\n",
" <td>-0.775184</td>\n",
" <td>-0.482252</td>\n",
" <td>1.079592</td>\n",
" <td>-0.774245</td>\n",
" <td>-0.341679</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>83</th>\n",
" <td>-1.501379</td>\n",
" <td>0.189171</td>\n",
" <td>-0.698559</td>\n",
" <td>-1.787276</td>\n",
" <td>-1.161708</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>84 rows × 10 columns</p>\n",
"</div>"
],
"text/plain": [
" Extraversion Agreeableness Conscientiousness Neuroticism Openness \\\n",
"0 0.193076 -0.258444 -0.031753 -0.976851 0.068336 \n",
"1 1.403400 -0.034637 0.857323 0.441392 1.093373 \n",
"2 -0.048989 -0.258444 -1.143097 -0.571639 -0.341679 \n",
"3 -1.017249 -1.153674 -2.476711 -1.584670 0.273343 \n",
"4 -1.017249 0.636786 -0.476290 -0.166427 -0.136672 \n",
".. ... ... ... ... ... \n",
"79 0.435140 1.532016 0.857323 -0.369033 0.068336 \n",
"80 -1.501379 -2.496519 -0.698559 -3.610732 -1.161708 \n",
"81 0.677205 0.189171 0.635054 0.441392 -0.341679 \n",
"82 -0.775184 -0.482252 1.079592 -0.774245 -0.341679 \n",
"83 -1.501379 0.189171 -0.698559 -1.787276 -1.161708 \n",
"\n",
" Breaking Dancehall Hip Hop House Vogue \n",
"0 0 0 0 1 0 \n",
"1 0 0 1 0 0 \n",
"2 0 1 0 0 0 \n",
"3 0 0 0 1 0 \n",
"4 0 0 1 0 0 \n",
".. ... ... ... ... ... \n",
"79 1 0 0 0 0 \n",
"80 0 0 1 0 0 \n",
"81 0 0 0 0 1 \n",
"82 0 0 1 0 0 \n",
"83 0 0 1 0 0 \n",
"\n",
"[84 rows x 10 columns]"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df= pd.concat([df_scaled, df_encoded], axis=1)\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "5f3f1779",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<Axes: >"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 6000x4000 with 2 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"\"\"\"\n",
"SECTION 5: Checking corelation\n",
"\"\"\"\n",
"#Create a corelation matrix to check the relation between Target and other Cols\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"plt.subplots(figsize=(60, 40))\n",
"sns.heatmap(df.corr(), annot = True)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "6fa78d00",
"metadata": {},
"outputs": [],
"source": [
"\"\"\"\n",
"SECTION 6: Splitting into Train/Test\n",
"\"\"\"\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"x = df.iloc[:, :5] \n",
"y = df.iloc[:, 5:] \n",
"\n",
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "8e15737c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy: 0.11538461538461539\n"
]
}
],
"source": [
"\"\"\"\n",
"In this section the data is being processed using Decision Tree\n",
"\"\"\"\n",
"\"\"\"\n",
"MODEL 1: SVC with cost sensitive approach\n",
"\"\"\"\n",
"from sklearn.svm import SVC\n",
"from sklearn.metrics import accuracy_score\n",
"\n",
"# Compute the class weights based on the inverse of the class frequencies\n",
"class_weights = (1 / np.sum(y_train, axis=0)).to_dict()\n",
"\n",
"class_names = y_train.columns.tolist()\n",
"class_dict = {}\n",
"for i in range(len(class_names)):\n",
" class_dict[i] = class_weights[class_names[i]]\n",
" \n",
"# Create a SVM classifier with cost-sensitive approach\n",
"classifier = SVC(class_weight=class_dict)\n",
"\n",
"# Convert one-hot encoded target variable to array of class labels\n",
"y_train_labels = np.argmax(y_train.values, axis=1)\n",
"y_test_labels = np.argmax(y_test.values, axis=1)\n",
"y_train_labels = y_train_labels.ravel()\n",
"y_test_labels = y_test_labels.ravel()\n",
"\n",
"# Train the classifier using the training data\n",
"classifier.fit(X_train, y_train_labels)\n",
"\n",
"# Make predictions on the testing data\n",
"y_pred_labels = classifier.predict(X_test)\n",
"\n",
"# Compute the accuracy of the classifier\n",
"accuracy = accuracy_score(y_test_labels, y_pred_labels)\n",
"print(\"Accuracy:\", accuracy)"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "72e5183a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Accuracy: 0.11538461538461539\n"
]
}
],
"source": [
"\"\"\"\n",
"MODEL 2: SVC with cost sensitive approach and OVO\n",
"\"\"\"\n",
"from sklearn.svm import SVC\n",
"from sklearn.metrics import accuracy_score\n",
"\n",
"# Compute the class weights based on the inverse of the class frequencies\n",
"class_weights = (1 / np.sum(y_train, axis=0)).to_dict()\n",
"\n",
"class_names = y_train.columns.tolist()\n",
"class_dict = {}\n",
"for i in range(len(class_names)):\n",
" class_dict[i] = class_weights[class_names[i]]\n",
" \n",
"# Create a SVM classifier with cost-sensitive approach\n",
"classifier = SVC(class_weight=class_dict, decision_function_shape='ovo')\n",
"\n",
"# Convert one-hot encoded target variable to array of class labels\n",
"y_train_labels = np.argmax(y_train.values, axis=1)\n",
"y_test_labels = np.argmax(y_test.values, axis=1)\n",
"y_train_labels = y_train_labels.ravel()\n",
"y_test_labels = y_test_labels.ravel()\n",
"\n",
"# Train the classifier using the training data\n",
"classifier.fit(X_train, y_train_labels)\n",
"\n",
"# Make predictions on the testing data\n",
"y_pred_labels = classifier.predict(X_test)\n",
"\n",
"# Compute the accuracy of the classifier\n",
"accuracy = accuracy_score(y_test_labels, y_pred_labels)\n",
"print(\"Accuracy:\", accuracy)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "19ee093a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Best parameters: {'C': 100, 'degree': 2, 'gamma': 'auto', 'kernel': 'rbf'}\n",
"Accuracy: 0.37982456140350873\n"
]
}
],
"source": [
"\"\"\"\n",
"Hypertuning will be performed to enchance the accuraccy\n",
"\"\"\"\n",
"from sklearn.model_selection import GridSearchCV\n",
"from sklearn.multiclass import OneVsOneClassifier, OneVsRestClassifier\n",
"\n",
"y_train_labels = np.argmax(y_train.values, axis=1)\n",
"y_test_labels = np.argmax(y_test.values, axis=1)\n",
"y_train_labels = y_train_labels.ravel()\n",
"y_test_labels = y_test_labels.ravel()\n",
"\n",
"# Compute the class weights based on the inverse of the class frequencies\n",
"class_weights = (1 / np.sum(y_train, axis=0)).to_dict()\n",
"\n",
"class_names = y_train.columns.tolist()\n",
"class_dict = {}\n",
"for i in range(len(class_names)):\n",
" class_dict[i] = class_weights[class_names[i]]\n",
"\n",
"param_grid = {'C': [0.1, 1, 10, 100],\n",
" 'kernel': ['linear', 'rbf', 'poly'],\n",
" 'degree': [2, 3, 4],\n",
" 'gamma': ['scale', 'auto']}\n",
"\n",
"svc = SVC(class_weight=class_dict)\n",
"\n",
"grid = GridSearchCV(estimator=svc, param_grid=param_grid, cv=3)\n",
"grid.fit(X_train, y_train_labels)\n",
"\n",
"print(\"Best parameters:\", grid.best_params_)\n",
"print(\"Accuracy:\", grid.best_score_)"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "dbf54c5a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Accuracy: 0.46\n",
"\n",
"Micro Precision: 0.46\n",
"Micro Recall: 0.46\n",
"Micro F1-score: 0.46\n",
"\n",
"Macro Precision: 0.36\n",
"Macro Recall: 0.33\n",
"Macro F1-score: 0.30\n",
"\n",
"Weighted Precision: 0.43\n",
"Weighted Recall: 0.46\n",
"Weighted F1-score: 0.42\n",
"\n",
"Classification Report\n",
"\n",
" precision recall f1-score support\n",
"\n",
" Breaking 1.00 0.33 0.50 3\n",
" Dancehall 0.29 0.67 0.40 3\n",
" Hip Hop 0.53 0.64 0.58 14\n",
" House 0.00 0.00 0.00 2\n",
" Vogue 0.00 0.00 0.00 4\n",
"\n",
" accuracy 0.46 26\n",
" macro avg 0.36 0.33 0.30 26\n",
"weighted avg 0.43 0.46 0.42 26\n",
"\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\DellG3\\anaconda3\\lib\\site-packages\\sklearn\\metrics\\_classification.py:1344: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
" _warn_prf(average, modifier, msg_start, len(result))\n",
"C:\\Users\\DellG3\\anaconda3\\lib\\site-packages\\sklearn\\metrics\\_classification.py:1344: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
" _warn_prf(average, modifier, msg_start, len(result))\n",
"C:\\Users\\DellG3\\anaconda3\\lib\\site-packages\\sklearn\\metrics\\_classification.py:1344: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
" _warn_prf(average, modifier, msg_start, len(result))\n",
"C:\\Users\\DellG3\\anaconda3\\lib\\site-packages\\sklearn\\metrics\\_classification.py:1344: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
" _warn_prf(average, modifier, msg_start, len(result))\n",
"C:\\Users\\DellG3\\anaconda3\\lib\\site-packages\\sklearn\\metrics\\_classification.py:1344: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
" _warn_prf(average, modifier, msg_start, len(result))\n"
]
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 640x480 with 2 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"\"\"\"\n",
"Best model fined by hypertuning - Precision, Recall and F1 score analysis \n",
"acc = accuracy_score(y_test_labels, y_pred_labels)\n",
"\"\"\"\n",
"classifier = SVC(class_weight=class_dict, C=100, degree=2, gamma='auto', kernel='rbf' )\n",
"\n",
"# Convert one-hot encoded target variable to array of class labels\n",
"y_train_labels = np.argmax(y_train.values, axis=1)\n",
"y_test_labels = np.argmax(y_test.values, axis=1)\n",
"y_train_labels = y_train_labels.ravel()\n",
"y_test_labels = y_test_labels.ravel()\n",
"\n",
"classifier.fit(X_train, y_train_labels)\n",
"y_pred_labels = classifier.predict(X_test)\n",
"\n",
"# Confusion matrix evaluation\n",
"from sklearn.metrics import confusion_matrix\n",
"confusion= confusion_matrix(y_test_labels, y_pred_labels)\n",
"confusion_matrix_plot=sns.heatmap(confusion, annot=True, xticklabels=['Breaking','Dancehall','Hip Hop','House', 'Vogue'], yticklabels=['Breaking','Dancehall','Hip Hop','House', 'Vogue'])\n",
"#confusion_matrix_plot.set(xlabel='Actual Values', ylabel='Predicted Values')\n",
"\n",
"#importing accuracy_score, precision_score, recall_score, f1_score\n",
"from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score\n",
"print('\\nAccuracy: {:.2f}\\n'.format(accuracy_score(y_test_labels, y_pred_labels)))\n",
"\n",
"print('Micro Precision: {:.2f}'.format(precision_score(y_test_labels, y_pred_labels, average='micro')))\n",
"print('Micro Recall: {:.2f}'.format(recall_score(y_test_labels, y_pred_labels, average='micro')))\n",
"print('Micro F1-score: {:.2f}\\n'.format(f1_score(y_test_labels, y_pred_labels, average='micro')))\n",
"\n",
"print('Macro Precision: {:.2f}'.format(precision_score(y_test_labels, y_pred_labels, average='macro')))\n",
"print('Macro Recall: {:.2f}'.format(recall_score(y_test_labels, y_pred_labels, average='macro')))\n",
"print('Macro F1-score: {:.2f}\\n'.format(f1_score(y_test_labels, y_pred_labels, average='macro')))\n",
"\n",
"print('Weighted Precision: {:.2f}'.format(precision_score(y_test_labels, y_pred_labels, average='weighted')))\n",
"print('Weighted Recall: {:.2f}'.format(recall_score(y_test_labels, y_pred_labels, average='weighted')))\n",
"print('Weighted F1-score: {:.2f}'.format(f1_score(y_test_labels, y_pred_labels, average='weighted')))\n",
"\n",
"from sklearn.metrics import classification_report\n",
"print('\\nClassification Report\\n')\n",
"print(classification_report(y_test_labels, y_pred_labels, target_names=['Breaking','Dancehall','Hip Hop','House', 'Vogue']))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "270fd370",
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}