{
"cells": [
{
"cell_type": "markdown",
"source": [
"## Introduction to Probability and Statistics\r\n",
"## Assignment\r\n",
"\r\n",
"In this assignment, we will use the dataset of diabetes patients taken [from here](https://www4.stat.ncsu.edu/~boos/var.select/diabetes.html)."
],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 13,
"source": [
"import pandas as pd\r\n",
"import numpy as np\r\n",
"import matplotlib.pyplot as plt\r\n",
"\r\n",
"df = pd.read_csv(\"../../../data/diabetes.tsv\",sep='\\t')\r\n",
"df.head()"
],
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" AGE SEX BMI BP S1 S2 S3 S4 S5 S6 Y\n",
"0 59 2 32.1 101.0 157 93.2 38.0 4.0 4.8598 87 151\n",
"1 48 1 21.6 87.0 183 103.2 70.0 3.0 3.8918 69 75\n",
"2 72 2 30.5 93.0 156 93.6 41.0 4.0 4.6728 85 141\n",
"3 24 1 25.3 84.0 198 131.4 40.0 5.0 4.8903 89 206\n",
"4 50 1 23.0 101.0 192 125.4 52.0 4.0 4.2905 80 135"
],
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" AGE | \n",
" SEX | \n",
" BMI | \n",
" BP | \n",
" S1 | \n",
" S2 | \n",
" S3 | \n",
" S4 | \n",
" S5 | \n",
" S6 | \n",
" Y | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" 59 | \n",
" 2 | \n",
" 32.1 | \n",
" 101.0 | \n",
" 157 | \n",
" 93.2 | \n",
" 38.0 | \n",
" 4.0 | \n",
" 4.8598 | \n",
" 87 | \n",
" 151 | \n",
"
\n",
" \n",
" 1 | \n",
" 48 | \n",
" 1 | \n",
" 21.6 | \n",
" 87.0 | \n",
" 183 | \n",
" 103.2 | \n",
" 70.0 | \n",
" 3.0 | \n",
" 3.8918 | \n",
" 69 | \n",
" 75 | \n",
"
\n",
" \n",
" 2 | \n",
" 72 | \n",
" 2 | \n",
" 30.5 | \n",
" 93.0 | \n",
" 156 | \n",
" 93.6 | \n",
" 41.0 | \n",
" 4.0 | \n",
" 4.6728 | \n",
" 85 | \n",
" 141 | \n",
"
\n",
" \n",
" 3 | \n",
" 24 | \n",
" 1 | \n",
" 25.3 | \n",
" 84.0 | \n",
" 198 | \n",
" 131.4 | \n",
" 40.0 | \n",
" 5.0 | \n",
" 4.8903 | \n",
" 89 | \n",
" 206 | \n",
"
\n",
" \n",
" 4 | \n",
" 50 | \n",
" 1 | \n",
" 23.0 | \n",
" 101.0 | \n",
" 192 | \n",
" 125.4 | \n",
" 52.0 | \n",
" 4.0 | \n",
" 4.2905 | \n",
" 80 | \n",
" 135 | \n",
"
\n",
" \n",
"
\n",
"
"
]
},
"metadata": {},
"execution_count": 13
}
],
"metadata": {}
},
{
"cell_type": "markdown",
"source": [
"\r\n",
"In this dataset, columns as the following:\r\n",
"* Age and sex are self-explanatory\r\n",
"* BMI is body mass index\r\n",
"* BP is average blood pressure\r\n",
"* S1 through S6 are different blood measurements\r\n",
"* Y is the qualitative measure of disease progression over one year\r\n",
"\r\n",
"Let's study this dataset using methods of probability and statistics.\r\n",
"\r\n",
"### Task 1: Compute mean values and variance for all values"
],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 5,
"source": [
"df.describe()"
],
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" AGE SEX BMI BP S1 S2 \\\n",
"count 442.000000 442.000000 442.000000 442.000000 442.000000 442.000000 \n",
"mean 48.518100 1.468326 26.375792 94.647014 189.140271 115.439140 \n",
"std 13.109028 0.499561 4.418122 13.831283 34.608052 30.413081 \n",
"min 19.000000 1.000000 18.000000 62.000000 97.000000 41.600000 \n",
"25% 38.250000 1.000000 23.200000 84.000000 164.250000 96.050000 \n",
"50% 50.000000 1.000000 25.700000 93.000000 186.000000 113.000000 \n",
"75% 59.000000 2.000000 29.275000 105.000000 209.750000 134.500000 \n",
"max 79.000000 2.000000 42.200000 133.000000 301.000000 242.400000 \n",
"\n",
" S3 S4 S5 S6 Y \n",
"count 442.000000 442.000000 442.000000 442.000000 442.000000 \n",
"mean 49.788462 4.070249 4.641411 91.260181 152.133484 \n",
"std 12.934202 1.290450 0.522391 11.496335 77.093005 \n",
"min 22.000000 2.000000 3.258100 58.000000 25.000000 \n",
"25% 40.250000 3.000000 4.276700 83.250000 87.000000 \n",
"50% 48.000000 4.000000 4.620050 91.000000 140.500000 \n",
"75% 57.750000 5.000000 4.997200 98.000000 211.500000 \n",
"max 99.000000 9.090000 6.107000 124.000000 346.000000 "
],
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" AGE | \n",
" SEX | \n",
" BMI | \n",
" BP | \n",
" S1 | \n",
" S2 | \n",
" S3 | \n",
" S4 | \n",
" S5 | \n",
" S6 | \n",
" Y | \n",
"
\n",
" \n",
" \n",
" \n",
" count | \n",
" 442.000000 | \n",
" 442.000000 | \n",
" 442.000000 | \n",
" 442.000000 | \n",
" 442.000000 | \n",
" 442.000000 | \n",
" 442.000000 | \n",
" 442.000000 | \n",
" 442.000000 | \n",
" 442.000000 | \n",
" 442.000000 | \n",
"
\n",
" \n",
" mean | \n",
" 48.518100 | \n",
" 1.468326 | \n",
" 26.375792 | \n",
" 94.647014 | \n",
" 189.140271 | \n",
" 115.439140 | \n",
" 49.788462 | \n",
" 4.070249 | \n",
" 4.641411 | \n",
" 91.260181 | \n",
" 152.133484 | \n",
"
\n",
" \n",
" std | \n",
" 13.109028 | \n",
" 0.499561 | \n",
" 4.418122 | \n",
" 13.831283 | \n",
" 34.608052 | \n",
" 30.413081 | \n",
" 12.934202 | \n",
" 1.290450 | \n",
" 0.522391 | \n",
" 11.496335 | \n",
" 77.093005 | \n",
"
\n",
" \n",
" min | \n",
" 19.000000 | \n",
" 1.000000 | \n",
" 18.000000 | \n",
" 62.000000 | \n",
" 97.000000 | \n",
" 41.600000 | \n",
" 22.000000 | \n",
" 2.000000 | \n",
" 3.258100 | \n",
" 58.000000 | \n",
" 25.000000 | \n",
"
\n",
" \n",
" 25% | \n",
" 38.250000 | \n",
" 1.000000 | \n",
" 23.200000 | \n",
" 84.000000 | \n",
" 164.250000 | \n",
" 96.050000 | \n",
" 40.250000 | \n",
" 3.000000 | \n",
" 4.276700 | \n",
" 83.250000 | \n",
" 87.000000 | \n",
"
\n",
" \n",
" 50% | \n",
" 50.000000 | \n",
" 1.000000 | \n",
" 25.700000 | \n",
" 93.000000 | \n",
" 186.000000 | \n",
" 113.000000 | \n",
" 48.000000 | \n",
" 4.000000 | \n",
" 4.620050 | \n",
" 91.000000 | \n",
" 140.500000 | \n",
"
\n",
" \n",
" 75% | \n",
" 59.000000 | \n",
" 2.000000 | \n",
" 29.275000 | \n",
" 105.000000 | \n",
" 209.750000 | \n",
" 134.500000 | \n",
" 57.750000 | \n",
" 5.000000 | \n",
" 4.997200 | \n",
" 98.000000 | \n",
" 211.500000 | \n",
"
\n",
" \n",
" max | \n",
" 79.000000 | \n",
" 2.000000 | \n",
" 42.200000 | \n",
" 133.000000 | \n",
" 301.000000 | \n",
" 242.400000 | \n",
" 99.000000 | \n",
" 9.090000 | \n",
" 6.107000 | \n",
" 124.000000 | \n",
" 346.000000 | \n",
"
\n",
" \n",
"
\n",
"
"
]
},
"metadata": {},
"execution_count": 5
}
],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 8,
"source": [
"# Another way\r\n",
"pd.DataFrame([df.mean(),df.var()],index=['Mean','Variance']).head()"
],
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" AGE SEX BMI BP S1 S2 \\\n",
"Mean 48.51810 1.468326 26.375792 94.647014 189.140271 115.439140 \n",
"Variance 171.84661 0.249561 19.519798 191.304401 1197.717241 924.955494 \n",
"\n",
" S3 S4 S5 S6 Y \n",
"Mean 49.788462 4.070249 4.641411 91.260181 152.133484 \n",
"Variance 167.293585 1.665261 0.272892 132.165712 5943.331348 "
],
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" AGE | \n",
" SEX | \n",
" BMI | \n",
" BP | \n",
" S1 | \n",
" S2 | \n",
" S3 | \n",
" S4 | \n",
" S5 | \n",
" S6 | \n",
" Y | \n",
"
\n",
" \n",
" \n",
" \n",
" Mean | \n",
" 48.51810 | \n",
" 1.468326 | \n",
" 26.375792 | \n",
" 94.647014 | \n",
" 189.140271 | \n",
" 115.439140 | \n",
" 49.788462 | \n",
" 4.070249 | \n",
" 4.641411 | \n",
" 91.260181 | \n",
" 152.133484 | \n",
"
\n",
" \n",
" Variance | \n",
" 171.84661 | \n",
" 0.249561 | \n",
" 19.519798 | \n",
" 191.304401 | \n",
" 1197.717241 | \n",
" 924.955494 | \n",
" 167.293585 | \n",
" 1.665261 | \n",
" 0.272892 | \n",
" 132.165712 | \n",
" 5943.331348 | \n",
"
\n",
" \n",
"
\n",
"
"
]
},
"metadata": {},
"execution_count": 8
}
],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 9,
"source": [
"# Or, more simply, for the mean (variance can be done similarly)\r\n",
"df.mean()"
],
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"AGE 48.518100\n",
"SEX 1.468326\n",
"BMI 26.375792\n",
"BP 94.647014\n",
"S1 189.140271\n",
"S2 115.439140\n",
"S3 49.788462\n",
"S4 4.070249\n",
"S5 4.641411\n",
"S6 91.260181\n",
"Y 152.133484\n",
"dtype: float64"
]
},
"metadata": {},
"execution_count": 9
}
],
"metadata": {}
},
{
"cell_type": "markdown",
"source": [
"### Task 2: Plot boxplots for BMI, BP and Y depending on gender"
],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 17,
"source": [
"for col in ['BMI','BP','Y']:\r\n",
" df.boxplot(column=col,by='SEX')\r\n",
"plt.show()"
],
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/svg+xml": "\r\n\r\n\r\n",
"image/png": "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"
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/svg+xml": "\r\n\r\n\r\n",
"image/png": "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"
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/svg+xml": "\r\n\r\n\r\n",
"image/png": "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"
},
"metadata": {}
}
],
"metadata": {}
},
{
"cell_type": "markdown",
"source": [
"### Task 3: What is the the distribution of Age, Sex, BMI and Y variables?"
],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 19,
"source": [
"for col in ['AGE','SEX','BMI','Y']:\r\n",
" df[col].hist()\r\n",
" plt.show()"
],
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/svg+xml": "\r\n\r\n\r\n",
"image/png": "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"
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/svg+xml": "\r\n\r\n\r\n",
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAigAAAGdCAYAAAA44ojeAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8rg+JYAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAfYklEQVR4nO3df2xV9f3H8dctLbcta5kF6e2VyqopUVfGFlCw6AChZTghjmWQsQxUdBh+mKYiEZnzdpr2GxaRWCLLEgQn8iM6cS5DaZ2zFTsTaCAKOoazQzqpDcj6e7eX9nz/cL1SW6AX74/3Lc9H0sR77rmnn/um9Tw5t+W6HMdxBAAAYEhCrBcAAADwVQQKAAAwh0ABAADmECgAAMAcAgUAAJhDoAAAAHMIFAAAYA6BAgAAzEmM9QIuRXd3tz799FOlpaXJ5XLFejkAAGAAHMdRS0uLvF6vEhIufI0kLgPl008/VXZ2dqyXAQAALsGJEyc0evToC+4Tl4GSlpYm6YsnmJ6eHtZjBwIBVVRUqLCwUElJSWE9Nr7EnKODOUcHc44eZh0dkZpzc3OzsrOzg+fxC4nLQOl5WSc9PT0igZKamqr09HS++COIOUcHc44O5hw9zDo6Ij3ngfx4Bj8kCwAAzCFQAACAOQQKAAAwh0ABAADmECgAAMAcAgUAAJhDoAAAAHMIFAAAYA6BAgAAzCFQAACAOQQKAAAwh0ABAADmECgAAMAcAgUAAJiTGOsFWJXn2yt/18XfDtqKf/3fD2O9BAAAwoYrKAAAwBwCBQAAmEOgAAAAcwgUAABgDoECAADMIVAAAIA5BAoAADCHQAEAAOYQKAAAwBwCBQAAmEOgAAAAcwgUAABgDoECAADMIVAAAIA5BAoAADCHQAEAAOYQKAAAwBwCBQAAmEOgAAAAcwgUAABgDoECAADMIVAAAIA5BAoAADCHQAEAAOYQKAAAwBwCBQAAmEOgAAAAcwgUAABgDoECAADMIVAAAIA5BAoAADCHQAEAAOYQKAAAwBwCBQAAmEOgAAAAcwgUAABgDoECAADMIVAAAIA5BAoAADCHQAEAAOYQKAAAwJzEWC8AAIDB7lsP/znWSwiJe4ijdTfFdg1cQQEAAOYQKAAAwBwCBQAAmEOgAAAAcwgUAABgDoECAADMCSlQysrKdOONNyotLU2jRo3SnXfeqaNHj/bax3Ec+Xw+eb1epaSkaNq0aTpy5Eivffx+v1auXKmRI0dq2LBhmjt3rurr67/+swEAAINCSIFSVVWl5cuX691331VlZaXOnj2rwsJCtbW1BfdZt26d1q9fr40bN2r//v3yeDwqKChQS0tLcJ+ioiLt3r1bO3fu1L59+9Ta2qo77rhDXV1d4XtmAAAgboX0D7W9/vrrvW5v2bJFo0aNUm1trb7//e/LcRxt2LBBa9eu1bx58yRJzz33nDIzM7V9+3YtXbpUTU1N2rx5s55//nnNnDlTkrRt2zZlZ2frjTfe0KxZs8L01AAAQLz6Wv+SbFNTkyQpIyNDklRXV6eGhgYVFhYG93G73Zo6dapqamq0dOlS1dbWKhAI9NrH6/UqLy9PNTU1/QaK3++X3+8P3m5ubpYkBQIBBQKBr/MU+ug5njvBCetxIy3cc4i0nvXG27rjDXOODuYcPfE6a/eQ+Dqn9JwDI3WOHYhLDhTHcVRcXKxbbrlFeXl5kqSGhgZJUmZmZq99MzMzdfz48eA+Q4cO1RVXXNFnn57Hf1VZWZlKSkr6bK+oqFBqauqlPoULenxid0SOGyl79uyJ9RIuSWVlZayXcFlgztHBnKMn3mYd6382/lKFe87t7e0D3veSA2XFihV67733tG/fvj73uVyuXrcdx+mz7asutM+aNWtUXFwcvN3c3Kzs7GwVFhYqPT39ElZ/foFAQJWVlXr0QIL83RdesyWHffH10ljPnAsKCpSUlBTr5QxazDk6mHP0xOus83x7Y72EkLgTHD0+sTvsc+55BWQgLilQVq5cqVdffVXV1dUaPXp0cLvH45H0xVWSrKys4PbGxsbgVRWPx6POzk6dOXOm11WUxsZG5efn9/v53G633G53n+1JSUkR+wL1d7vk74qfQImnb9RzRfLPEF9iztHBnKMn3mYdT+eTc4V7zqEcK6Tf4nEcRytWrNDLL7+sN998Uzk5Ob3uz8nJkcfj6XVJqLOzU1VVVcH4mDBhgpKSknrtc/LkSR0+fPi8gQIAAC4vIV1BWb58ubZv364//vGPSktLC/7MyPDhw5WSkiKXy6WioiKVlpYqNzdXubm5Ki0tVWpqqhYuXBjcd8mSJXrwwQc1YsQIZWRkaNWqVRo3blzwt3oAAMDlLaRA2bRpkyRp2rRpvbZv2bJFd911lyRp9erV6ujo0LJly3TmzBlNmjRJFRUVSktLC+7/1FNPKTExUfPnz1dHR4dmzJihrVu3asiQIV/v2QAAgEEhpEBxnIv/mpTL5ZLP55PP5zvvPsnJySovL1d5eXkonx4AAFwmeC8eAABgDoECAADMIVAAAIA5BAoAADCHQAEAAOYQKAAAwBwCBQAAmEOgAAAAcwgUAABgDoECAADMIVAAAIA5BAoAADCHQAEAAOYQKAAAwBwCBQAAmEOgAAAAcwgUAABgDoECAADMIVAAAIA5BAoAADCHQAEAAOYQKAAAwBwCBQAAmEOgAAAAcwgUAABgDoECAADMIVAAAIA5BAoAADCHQAEAAOYQKAAAwBwCBQAAmEOgAAAAcwgUAABgDoECAADMIVAAAIA5BAoAADCHQAEAAOYQKAAAwBwCBQAAmEOgAAAAcwgUAABgDoECAADMIVAAAIA5BAoAADCHQAEAAOYQKAAAwBwCBQAAmEOgAAAAcwgUAABgDoECAADMIVAAAIA5BAoAADCHQAEAAOYQKAAAwBwCBQAAmEOgAAAAcwgUAABgDoECAADMIVAAAIA5BAoAADCHQAEAAOYQKAAAwBwCBQAAmBNyoFRXV2vOnDnyer1yuVx65ZVXet1/1113yeVy9fqYPHlyr338fr9WrlypkSNHatiwYZo7d67q6+u/1hMBAACDR8iB0tbWpvHjx2vjxo3n3ecHP/iBTp48GfzYs2dPr/uLioq0e/du7dy5U/v27VNra6vuuOMOdXV1hf4MAADAoJMY6gNmz56t2bNnX3Aft9stj8fT731NTU3avHmznn/+ec2cOVOStG3bNmVnZ+uNN97QrFmzQl0SAAAYZCLyMyhvvfWWRo0apbFjx+q+++5TY2Nj8L7a2loFAgEVFhYGt3m9XuXl5ammpiYSywEAAHEm5CsoFzN79mz95Cc/0ZgxY1RXV6dHH31Ut912m2pra+V2u9XQ0KChQ4fqiiuu6PW4zMxMNTQ09HtMv98vv98fvN3c3CxJCgQCCgQCYV1/z/HcCU5Yjxtp4Z5DpPWsN97WHW+Yc3Qw5+iJ11m7h8TXOaXnHBipc+xAhD1QFixYEPzvvLw8TZw4UWPGjNGf//xnzZs377yPcxxHLper3/vKyspUUlLSZ3tFRYVSU1O//qL78fjE7ogcN1K++nM+8aKysjLWS7gsMOfoYM7RE2+zXndTrFdwacI95/b29gHvG/ZA+aqsrCyNGTNGx44dkyR5PB51dnbqzJkzva6iNDY2Kj8/v99jrFmzRsXFxcHbzc3Nys7OVmFhodLT08O63kAgoMrKSj16IEH+7v6DyaLDvvj62Z2eORcUFCgpKSnWyxm0mHN0MOfoiddZ5/n2xnoJIXEnOHp8YnfY59zzCshARDxQTp8+rRMnTigrK0uSNGHCBCUlJamyslLz58+XJJ08eVKHDx/WunXr+j2G2+2W2+3usz0pKSliX6D+bpf8XfETKPH0jXquSP4Z4kvMOTqYc/TE26zj6XxyrnDPOZRjhRwora2t+uijj4K36+rqdOjQIWVkZCgjI0M+n08//vGPlZWVpX/961965JFHNHLkSP3oRz+SJA0fPlxLlizRgw8+qBEjRigjI0OrVq3SuHHjgr/VAwAALm8hB8qBAwc0ffr04O2el14WL16sTZs26f3339fvf/97/ec//1FWVpamT5+uXbt2KS0tLfiYp556SomJiZo/f746Ojo0Y8YMbd26VUOGDAnDUwIAAPEu5ECZNm2aHOf8P428d+/FX2dLTk5WeXm5ysvLQ/30AADgMsB78QAAAHMIFAAAYA6BAgAAzCFQAACAOQQKAAAwh0ABAADmECgAAMAcAgUAAJhDoAAAAHMIFAAAYA6BAgAAzCFQAACAOQQKAAAwh0ABAADmECgAAMAcAgUAAJhDoAAAAHMIFAAAYA6BAgAAzCFQAACAOQQKAAAwh0ABAADmECgAAMAcAgUAAJhDoAAAAHMIFAAAYA6BAgAAzCFQAACAOQQKAAAwh0ABAADmECgAAMAcAgUAAJhDoAAAAHMIFAAAYA6BAgAAzCFQAACAOQQKAAAwh0ABAADmECgAAMAcAgUAAJhDoAAAAHMIFAAAYA6BAgAAzCFQAACAOQQKAAAwh0ABAADmECgAAMAcAgUAAJhDoAAAAHMIFAAAYA6BAgAAzCFQAACAOQQKAAAwh0ABAADmECgAAMAcAgUAAJhDoAAAAHMIFAAAYA6BAgAAzCFQAACAOQQKAAAwh0ABAADmECgAAMAcAgUAAJgTcqBUV1drzpw58nq9crlceuWVV3rd7ziOfD6fvF6vUlJSNG3aNB05cqTXPn6/XytXrtTIkSM1bNgwzZ07V/X19V/riQAAgMEj5EBpa2vT+PHjtXHjxn7vX7dundavX6+NGzdq//798ng8KigoUEtLS3CfoqIi7d69Wzt37tS+ffvU2tqqO+64Q11dXZf+TAAAwKCRGOoDZs+erdmzZ/d7n+M42rBhg9auXat58+ZJkp577jllZmZq+/btWrp0qZqamrR582Y9//zzmjlzpiRp27Ztys7O1htvvKFZs2Z9jacDAAAGg5AD5ULq6urU0NCgwsLC4Da3262pU6eqpqZGS5cuVW1trQKBQK99vF6v8vLyVFNT02+g+P1++f3+4O3m5mZJUiAQUCAQCOdTCB7PneCE9biRFu45RFrPeuNt3fGGOUcHc46eeJ21e0h8nVN6zoGROscORFgDpaGhQZKUmZnZa3tmZqaOHz8e3Gfo0KG64oor+uzT8/ivKisrU0lJSZ/tFRUVSk1NDcfS+3h8YndEjhspe/bsifUSLkllZWWsl3BZYM7RwZyjJ95mve6mWK/g0oR7zu3t7QPeN6yB0sPlcvW67ThOn21fdaF91qxZo+Li4uDt5uZmZWdnq7CwUOnp6V9/wecIBAKqrKzUowcS5O++8JotOeyLr5fGeuZcUFCgpKSkWC9n0GLO0cGcoydeZ53n2xvrJYTEneDo8YndYZ9zzysgAxHWQPF4PJK+uEqSlZUV3N7Y2Bi8quLxeNTZ2akzZ870uorS2Nio/Pz8fo/rdrvldrv7bE9KSorYF6i/2yV/V/wESjx9o54rkn+G+BJzjg7mHD3xNut4Op+cK9xzDuVYYf13UHJycuTxeHpdEurs7FRVVVUwPiZMmKCkpKRe+5w8eVKHDx8+b6AAAIDLS8hXUFpbW/XRRx8Fb9fV1enQoUPKyMjQ1VdfraKiIpWWlio3N1e5ubkqLS1VamqqFi5cKEkaPny4lixZogcffFAjRoxQRkaGVq1apXHjxgV/qwcAAFzeQg6UAwcOaPr06cHbPT8bsnjxYm3dulWrV69WR0eHli1bpjNnzmjSpEmqqKhQWlpa8DFPPfWUEhMTNX/+fHV0dGjGjBnaunWrhgwZEoanBAAA4l3IgTJt2jQ5zvl/Xcrlcsnn88nn8513n+TkZJWXl6u8vDzUTw8AAC4DvBcPAAAwh0ABAADmECgAAMAcAgUAAJhDoAAAAHMIFAAAYA6BAgAAzCFQAACAOQQKAAAwh0ABAADmECgAAMAcAgUAAJhDoAAAAHMIFAAAYA6BAgAAzCFQAACAOQQKAAAwh0ABAADmECgAAMAcAgUAAJhDoAAAAHMIFAAAYA6BAgAAzCFQAACAOQQKAAAwh0ABAADmECgAAMAcAgUAAJhDoAAAAHMIFAAAYA6BAgAAzCFQAACAOQQKAAAwh0ABAADmECgAAMAcAgUAAJhDoAAAAHMIFAAAYA6BAgAAzCFQAACAOQQKAAAwh0ABAADmECgAAMAcAgUAAJhDoAAAAHMIFAAAYA6BAgAAzCFQAACAOQQKAAAwh0ABAADmECgAAMAcAgUAAJhDoAAAAHMIFAAAYA6BAgAAzCFQAACAOQQKAAAwh0ABAADmECgAAMAcAgUAAJhDoAAAAHMIFAAAYA6BAgAAzCFQAACAOWEPFJ/PJ5fL1evD4/EE73ccRz6fT16vVykpKZo2bZqOHDkS7mUAAIA4FpErKN/+9rd18uTJ4Mf7778fvG/dunVav369Nm7cqP3798vj8aigoEAtLS2RWAoAAIhDEQmUxMREeTye4MeVV14p6YurJxs2bNDatWs1b9485eXl6bnnnlN7e7u2b98eiaUAAIA4lBiJgx47dkxer1dut1uTJk1SaWmprrnmGtXV1amhoUGFhYXBfd1ut6ZOnaqamhotXbq03+P5/X75/f7g7ebmZklSIBBQIBAI69p7judOcMJ63EgL9xwirWe98bbueMOco4M5R0+8zto9JL7OKT3nwEidYwfC5ThOWKf22muvqb29XWPHjtVnn32mJ554Qn//+9915MgRHT16VFOmTNG///1veb3e4GN+8Ytf6Pjx49q7d2+/x/T5fCopKemzffv27UpNTQ3n8gEAQIS0t7dr4cKFampqUnp6+gX3DXugfFVbW5uuvfZarV69WpMnT9aUKVP06aefKisrK7jPfffdpxMnTuj111/v9xj9XUHJzs7WqVOnLvoEQxUIBFRZWalHDyTI3+0K67Ej6bBvVqyXEJKeORcUFCgpKSnWyxm0mHN0MOfoiddZ5/n6/wu4Ve4ER49P7A77nJubmzVy5MgBBUpEXuI517BhwzRu3DgdO3ZMd955pySpoaGhV6A0NjYqMzPzvMdwu91yu919ticlJUXsC9Tf7ZK/K34CJZ6+Uc8VyT9DfIk5Rwdzjp54m3U8nU/OFe45h3KsiP87KH6/Xx9++KGysrKUk5Mjj8ejysrK4P2dnZ2qqqpSfn5+pJcCAADiRNivoKxatUpz5szR1VdfrcbGRj3xxBNqbm7W4sWL5XK5VFRUpNLSUuXm5io3N1elpaVKTU3VwoULw70UAAAQp8IeKPX19frpT3+qU6dO6corr9TkyZP17rvvasyYMZKk1atXq6OjQ8uWLdOZM2c0adIkVVRUKC0tLdxLAQAAcSrsgbJz584L3u9yueTz+eTz+cL9qQEAwCDBe/EAAABzCBQAAGAOgQIAAMwhUAAAgDkECgAAMIdAAQAA5hAoAADAHAIFAACYQ6AAAABzCBQAAGAOgQIAAMwhUAAAgDkECgAAMIdAAQAA5hAoAADAHAIFAACYQ6AAAABzCBQAAGAOgQIAAMwhUAAAgDkECgAAMIdAAQAA5hAoAADAHAIFAACYQ6AAAABzCBQAAGAOgQIAAMwhUAAAgDkECgAAMIdAAQAA5hAoAADAHAIFAACYQ6AAAABzCBQAAGAOgQIAAMwhUAAAgDkECgAAMIdAAQAA5hAoAADAHAIFAACYQ6AAAABzCBQAAGAOgQIAAMwhUAAAgDkECgAAMIdAAQAA5hAoAADAHAIFAACYQ6AAAABzCBQAAGAOgQIAAMwhUAAAgDkECgAAMIdAAQAA5hAoAADAHAIFAACYQ6AAAABzCBQAAGAOgQIAAMwhUAAAgDkECgAAMIdAAQAA5hAoAADAHAIFAACYE9NAeeaZZ5STk6Pk5GRNmDBBb7/9diyXAwAAjIhZoOzatUtFRUVau3atDh48qFtvvVWzZ8/WJ598EqslAQAAI2IWKOvXr9eSJUt077336vrrr9eGDRuUnZ2tTZs2xWpJAADAiMRYfNLOzk7V1tbq4Ycf7rW9sLBQNTU1ffb3+/3y+/3B201NTZKkzz//XIFAIKxrCwQCam9vV2IgQV3drrAeO5JOnz4d6yWEpGfOp0+fVlJSUqyXM2gx5+hgztETr7NOPNsW6yWEJLHbUXt7d9jn3NLSIklyHOfiawjbZw3BqVOn1NXVpczMzF7bMzMz1dDQ0Gf/srIylZSU9Nmek5MTsTXGm5FPxnoFAIDBZGEEj93S0qLhw4dfcJ+YBEoPl6v3FQrHcfpsk6Q1a9aouLg4eLu7u1uff/65RowY0e/+X0dzc7Oys7N14sQJpaenh/XY+BJzjg7mHB3MOXqYdXREas6O46ilpUVer/ei+8YkUEaOHKkhQ4b0uVrS2NjY56qKJLndbrnd7l7bvvnNb0ZyiUpPT+eLPwqYc3Qw5+hgztHDrKMjEnO+2JWTHjH5IdmhQ4dqwoQJqqys7LW9srJS+fn5sVgSAAAwJGYv8RQXF+vnP/+5Jk6cqJtvvlm/+93v9Mknn+j++++P1ZIAAIARMQuUBQsW6PTp0/r1r3+tkydPKi8vT3v27NGYMWNitSRJX7yc9Nhjj/V5SQnhxZyjgzlHB3OOHmYdHRbm7HIG8rs+AAAAUcR78QAAAHMIFAAAYA6BAgAAzCFQAACAOZdVoFRXV2vOnDnyer1yuVx65ZVXLvqYqqoqTZgwQcnJybrmmmv029/+NvILHQRCnfXLL7+sgoICXXnllUpPT9fNN9+svXv3RmexcexSvqZ7vPPOO0pMTNR3v/vdiK1vsLiUOfv9fq1du1ZjxoyR2+3Wtddeq2effTbyi41jlzLnF154QePHj1dqaqqysrJ09913x917k0VbWVmZbrzxRqWlpWnUqFG68847dfTo0Ys+Ltrnw8sqUNra2jR+/Hht3LhxQPvX1dXp9ttv16233qqDBw/qkUce0QMPPKA//OEPEV5p/At11tXV1SooKNCePXtUW1ur6dOna86cOTp48GCEVxrfQp1zj6amJi1atEgzZsyI0MoGl0uZ8/z58/WXv/xFmzdv1tGjR7Vjxw5dd911EVxl/At1zvv27dOiRYu0ZMkSHTlyRC+++KL279+ve++9N8IrjW9VVVVavny53n33XVVWVurs2bMqLCxUW9v539AwJudD5zIlydm9e/cF91m9erVz3XXX9dq2dOlSZ/LkyRFc2eAzkFn354YbbnBKSkrCv6BBKpQ5L1iwwPnlL3/pPPbYY8748eMjuq7BZiBzfu2115zhw4c7p0+fjs6iBqGBzPk3v/mNc8011/Ta9vTTTzujR4+O4MoGn8bGRkeSU1VVdd59YnE+vKyuoITqb3/7mwoLC3ttmzVrlg4cOKBAIBCjVV0euru71dLSooyMjFgvZdDZsmWL/vnPf+qxxx6L9VIGrVdffVUTJ07UunXrdNVVV2ns2LFatWqVOjo6Yr20QSU/P1/19fXas2ePHMfRZ599ppdeekk//OEPY720uNLU1CRJF/z/bSzOhzF9N2PrGhoa+rx5YWZmps6ePatTp04pKysrRisb/J588km1tbVp/vz5sV7KoHLs2DE9/PDDevvtt5WYyLd/pHz88cfat2+fkpOTtXv3bp06dUrLli3T559/zs+hhFF+fr5eeOEFLViwQP/973919uxZzZ07V+Xl5bFeWtxwHEfFxcW65ZZblJeXd979YnE+5ArKRbhcrl63nf/9w7tf3Y7w2bFjh3w+n3bt2qVRo0bFejmDRldXlxYuXKiSkhKNHTs21ssZ1Lq7u+VyufTCCy/opptu0u23367169dr69atXEUJow8++EAPPPCAfvWrX6m2tlavv/666urqeE+3EKxYsULvvfeeduzYcdF9o30+5K9QF+DxeNTQ0NBrW2NjoxITEzVixIgYrWpw27Vrl5YsWaIXX3xRM2fOjPVyBpWWlhYdOHBABw8e1IoVKyR9cSJ1HEeJiYmqqKjQbbfdFuNVDg5ZWVm66qqrer2t/PXXXy/HcVRfX6/c3NwYrm7wKCsr05QpU/TQQw9Jkr7zne9o2LBhuvXWW/XEE09wlfsiVq5cqVdffVXV1dUaPXr0BfeNxfmQQLmAm2++WX/60596bauoqNDEiROVlJQUo1UNXjt27NA999yjHTt28BpyBKSnp+v999/vte2ZZ57Rm2++qZdeekk5OTkxWtngM2XKFL344otqbW3VN77xDUnSP/7xDyUkJFz0RICBa29v7/NS5ZAhQyR9+bd79OU4jlauXKndu3frrbfeGtD3fizOh5fVSzytra06dOiQDh06JOmLX5s6dOiQPvnkE0nSmjVrtGjRouD+999/v44fP67i4mJ9+OGHevbZZ7V582atWrUqFsuPK6HOeseOHVq0aJGefPJJTZ48WQ0NDWpoaAj+8Bb6F8qcExISlJeX1+tj1KhRSk5OVl5enoYNGxarp2FeqF/PCxcu1IgRI3T33Xfrgw8+UHV1tR566CHdc889SklJicVTiAuhznnOnDl6+eWXtWnTJn388cd655139MADD+imm26S1+uNxVOIC8uXL9e2bdu0fft2paWlBf9/e+7LjybOhxH7/SCD/vrXvzqS+nwsXrzYcRzHWbx4sTN16tRej3nrrbec733ve87QoUOdb33rW86mTZuiv/A4FOqsp06desH90b9L+Zo+F79mPDCXMucPP/zQmTlzppOSkuKMHj3aKS4udtrb26O/+DhyKXN++umnnRtuuMFJSUlxsrKynJ/97GdOfX199BcfR/qbsSRny5YtwX0snA9d/1ssAACAGZfVSzwAACA+ECgAAMAcAgUAAJhDoAAAAHMIFAAAYA6BAgAAzCFQAACAOQQKAAAwh0ABAADmECgAAMAcAgUAAJhDoAAAAHP+H9RcMUYy5VxzAAAAAElFTkSuQmCC"
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/svg+xml": "\r\n\r\n\r\n",
"image/png": "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"
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/svg+xml": "\r\n\r\n\r\n",
"image/png": "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"
},
"metadata": {}
}
],
"metadata": {}
},
{
"cell_type": "markdown",
"source": [
"Conclusions:\r\n",
"* Age - normal\r\n",
"* Sex - uniform\r\n",
"* BMI, Y - hard to tell"
],
"metadata": {}
},
{
"cell_type": "markdown",
"source": [
"### Task 4: Test the correlation between different variables and disease progression (Y)\r\n",
"\r\n",
"> **Hint** Correlation matrix would give you the most useful information on which values are dependent."
],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 20,
"source": [
"df.corr()"
],
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" AGE SEX BMI BP S1 S2 S3 \\\n",
"AGE 1.000000 0.173737 0.185085 0.335428 0.260061 0.219243 -0.075181 \n",
"SEX 0.173737 1.000000 0.088161 0.241010 0.035277 0.142637 -0.379090 \n",
"BMI 0.185085 0.088161 1.000000 0.395411 0.249777 0.261170 -0.366811 \n",
"BP 0.335428 0.241010 0.395411 1.000000 0.242464 0.185548 -0.178762 \n",
"S1 0.260061 0.035277 0.249777 0.242464 1.000000 0.896663 0.051519 \n",
"S2 0.219243 0.142637 0.261170 0.185548 0.896663 1.000000 -0.196455 \n",
"S3 -0.075181 -0.379090 -0.366811 -0.178762 0.051519 -0.196455 1.000000 \n",
"S4 0.203841 0.332115 0.413807 0.257650 0.542207 0.659817 -0.738493 \n",
"S5 0.270774 0.149916 0.446157 0.393480 0.515503 0.318357 -0.398577 \n",
"S6 0.301731 0.208133 0.388680 0.390430 0.325717 0.290600 -0.273697 \n",
"Y 0.187889 0.043062 0.586450 0.441482 0.212022 0.174054 -0.394789 \n",
"\n",
" S4 S5 S6 Y \n",
"AGE 0.203841 0.270774 0.301731 0.187889 \n",
"SEX 0.332115 0.149916 0.208133 0.043062 \n",
"BMI 0.413807 0.446157 0.388680 0.586450 \n",
"BP 0.257650 0.393480 0.390430 0.441482 \n",
"S1 0.542207 0.515503 0.325717 0.212022 \n",
"S2 0.659817 0.318357 0.290600 0.174054 \n",
"S3 -0.738493 -0.398577 -0.273697 -0.394789 \n",
"S4 1.000000 0.617859 0.417212 0.430453 \n",
"S5 0.617859 1.000000 0.464669 0.565883 \n",
"S6 0.417212 0.464669 1.000000 0.382483 \n",
"Y 0.430453 0.565883 0.382483 1.000000 "
],
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" AGE | \n",
" SEX | \n",
" BMI | \n",
" BP | \n",
" S1 | \n",
" S2 | \n",
" S3 | \n",
" S4 | \n",
" S5 | \n",
" S6 | \n",
" Y | \n",
"
\n",
" \n",
" \n",
" \n",
" AGE | \n",
" 1.000000 | \n",
" 0.173737 | \n",
" 0.185085 | \n",
" 0.335428 | \n",
" 0.260061 | \n",
" 0.219243 | \n",
" -0.075181 | \n",
" 0.203841 | \n",
" 0.270774 | \n",
" 0.301731 | \n",
" 0.187889 | \n",
"
\n",
" \n",
" SEX | \n",
" 0.173737 | \n",
" 1.000000 | \n",
" 0.088161 | \n",
" 0.241010 | \n",
" 0.035277 | \n",
" 0.142637 | \n",
" -0.379090 | \n",
" 0.332115 | \n",
" 0.149916 | \n",
" 0.208133 | \n",
" 0.043062 | \n",
"
\n",
" \n",
" BMI | \n",
" 0.185085 | \n",
" 0.088161 | \n",
" 1.000000 | \n",
" 0.395411 | \n",
" 0.249777 | \n",
" 0.261170 | \n",
" -0.366811 | \n",
" 0.413807 | \n",
" 0.446157 | \n",
" 0.388680 | \n",
" 0.586450 | \n",
"
\n",
" \n",
" BP | \n",
" 0.335428 | \n",
" 0.241010 | \n",
" 0.395411 | \n",
" 1.000000 | \n",
" 0.242464 | \n",
" 0.185548 | \n",
" -0.178762 | \n",
" 0.257650 | \n",
" 0.393480 | \n",
" 0.390430 | \n",
" 0.441482 | \n",
"
\n",
" \n",
" S1 | \n",
" 0.260061 | \n",
" 0.035277 | \n",
" 0.249777 | \n",
" 0.242464 | \n",
" 1.000000 | \n",
" 0.896663 | \n",
" 0.051519 | \n",
" 0.542207 | \n",
" 0.515503 | \n",
" 0.325717 | \n",
" 0.212022 | \n",
"
\n",
" \n",
" S2 | \n",
" 0.219243 | \n",
" 0.142637 | \n",
" 0.261170 | \n",
" 0.185548 | \n",
" 0.896663 | \n",
" 1.000000 | \n",
" -0.196455 | \n",
" 0.659817 | \n",
" 0.318357 | \n",
" 0.290600 | \n",
" 0.174054 | \n",
"
\n",
" \n",
" S3 | \n",
" -0.075181 | \n",
" -0.379090 | \n",
" -0.366811 | \n",
" -0.178762 | \n",
" 0.051519 | \n",
" -0.196455 | \n",
" 1.000000 | \n",
" -0.738493 | \n",
" -0.398577 | \n",
" -0.273697 | \n",
" -0.394789 | \n",
"
\n",
" \n",
" S4 | \n",
" 0.203841 | \n",
" 0.332115 | \n",
" 0.413807 | \n",
" 0.257650 | \n",
" 0.542207 | \n",
" 0.659817 | \n",
" -0.738493 | \n",
" 1.000000 | \n",
" 0.617859 | \n",
" 0.417212 | \n",
" 0.430453 | \n",
"
\n",
" \n",
" S5 | \n",
" 0.270774 | \n",
" 0.149916 | \n",
" 0.446157 | \n",
" 0.393480 | \n",
" 0.515503 | \n",
" 0.318357 | \n",
" -0.398577 | \n",
" 0.617859 | \n",
" 1.000000 | \n",
" 0.464669 | \n",
" 0.565883 | \n",
"
\n",
" \n",
" S6 | \n",
" 0.301731 | \n",
" 0.208133 | \n",
" 0.388680 | \n",
" 0.390430 | \n",
" 0.325717 | \n",
" 0.290600 | \n",
" -0.273697 | \n",
" 0.417212 | \n",
" 0.464669 | \n",
" 1.000000 | \n",
" 0.382483 | \n",
"
\n",
" \n",
" Y | \n",
" 0.187889 | \n",
" 0.043062 | \n",
" 0.586450 | \n",
" 0.441482 | \n",
" 0.212022 | \n",
" 0.174054 | \n",
" -0.394789 | \n",
" 0.430453 | \n",
" 0.565883 | \n",
" 0.382483 | \n",
" 1.000000 | \n",
"
\n",
" \n",
"
\n",
"
"
]
},
"metadata": {},
"execution_count": 20
}
],
"metadata": {}
},
{
"cell_type": "markdown",
"source": [
"Conclusion:\r\n",
"* The strongest correlation of Y is BMI and S5 (blood sugar). This sounds reasonable."
],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 26,
"source": [
"fig, ax = plt.subplots(1,3,figsize=(10,5))\r\n",
"for i,n in enumerate(['BMI','S5','BP']):\r\n",
" ax[i].scatter(df['Y'],df[n])\r\n",
" ax[i].set_title(n)\r\n",
"plt.show()"
],
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"