date.ipynb

rats_biochemistry.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Анализ биохимии"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# install.packages(c(\"gridExtra\", \"ggsignif\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "library(gridExtra)\n",
    "library(ggplot2)\n",
    "library(ggsignif)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# графики"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "biochemistry <- read.csv(\"biochemistry.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "title <- 'Результаты анализов биохимии'\n",
    "x_label <- 'Группы'\n",
    "y_label <- 'МЕ/л'\n",
    "group_labels <- c(\"Спирт\", \"Интактная\", \"Парацетамол\", \"Водка\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [
    {
     "data": {},
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA0gAAANICAIAAAByhViMAAAACXBIWXMAABJ0AAASdAHeZh94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\nRU5ErkJggg==",
      "text/plain": [
       "plot without title"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ggplot(biochemistry, aes(group, value, fill = group)) +\n",
    "    geom_boxplot() +\n",
    "    stat_boxplot(geom = \"errorbar\", width = 0.5) +\n",
    "    scale_x_discrete() +\n",
    "    scale_fill_brewer(palette = \"Set3\",\n",
    "                      name = x_label,\n",
    "                      labels = group_labels) +\n",
    "    theme_bw() +\n",
    "    theme(axis.text.x = element_blank(),\n",
    "          axis.text.y = element_text(angle = 60, hjust = 0.5, size = 8)) +\n",
    "    labs(title = title,\n",
    "         x = element_blank(),\n",
    "         y = y_label) +\n",
    "    facet_wrap(~ chem, scales = 'free_y', ncol = 4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "ggsave(\"biochemistry.png\", scale = 1, width = 25, height = 10, units = \"cm\", dpi = 300)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Корреляционный анализ\n",
    "\n",
    "Критерий Манна-Уитни-Вилкоксона\n",
    "\n",
    "## Сравнение парацетамол ~ интактная группа\n",
    "\n",
    "### ALP"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tWilcoxon rank sum test\n",
       "\n",
       "data:  value by group\n",
       "W = 4, p-value = 0.0001299\n",
       "alternative hypothesis: true location shift is not equal to 0\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "wilcox.test(value ~ group, subset = chem %in% 'ALP' & group %in% c('intact', 'paracetamol'),\n",
    "            data = biochemistry, paired = FALSE)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### ALT"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tWilcoxon rank sum test\n",
       "\n",
       "data:  value by group\n",
       "W = 15, p-value = 0.006841\n",
       "alternative hypothesis: true location shift is not equal to 0\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "wilcox.test(value ~ group, subset = chem %in% 'ALT' & group %in% c('intact', 'paracetamol'),\n",
    "            data = biochemistry, paired = FALSE)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### AST"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tWilcoxon rank sum test\n",
       "\n",
       "data:  value by group\n",
       "W = 30, p-value = 0.1431\n",
       "alternative hypothesis: true location shift is not equal to 0\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "wilcox.test(value ~ group, subset = chem %in% 'AST' & group %in% c('intact', 'paracetamol'),\n",
    "            data = biochemistry, paired = FALSE)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### LDH"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tWilcoxon rank sum test\n",
       "\n",
       "data:  value by group\n",
       "W = 7, p-value = 0.0004871\n",
       "alternative hypothesis: true location shift is not equal to 0\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "wilcox.test(value ~ group, subset = chem %in% 'LDH' & group %in% c('intact', 'paracetamol'),\n",
    "            data = biochemistry, paired = FALSE)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Сравнение спирт ~ интактная группа\n",
    "\n",
    "### ALP"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tWilcoxon rank sum test\n",
       "\n",
       "data:  value by group\n",
       "W = 43, p-value = 0.6305\n",
       "alternative hypothesis: true location shift is not equal to 0\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "wilcox.test(value ~ group, subset = chem %in% 'ALP' & group %in% c('intact', 'alcohol'),\n",
    "            data = biochemistry, paired = FALSE)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### ALT"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tWilcoxon rank sum test\n",
       "\n",
       "data:  value by group\n",
       "W = 7, p-value = 0.0004871\n",
       "alternative hypothesis: true location shift is not equal to 0\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "wilcox.test(value ~ group, subset = chem %in% 'ALT' & group %in% c('intact', 'alcohol'),\n",
    "            data = biochemistry, paired = FALSE)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### AST"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tWilcoxon rank sum test\n",
       "\n",
       "data:  value by group\n",
       "W = 31, p-value = 0.1655\n",
       "alternative hypothesis: true location shift is not equal to 0\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "wilcox.test(value ~ group, subset = chem %in% 'AST' & group %in% c('intact', 'alcohol'),\n",
    "            data = biochemistry, paired = FALSE)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### LDH"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tWilcoxon rank sum test\n",
       "\n",
       "data:  value by group\n",
       "W = 50, p-value = 1\n",
       "alternative hypothesis: true location shift is not equal to 0\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "wilcox.test(value ~ group, subset = chem %in% 'LDH' & group %in% c('intact', 'alcohol'),\n",
    "            data = biochemistry, paired = FALSE)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Сравнение водка ~ интактная группа\n",
    "\n",
    "### ALP"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tWilcoxon rank sum test\n",
       "\n",
       "data:  value by group\n",
       "W = 66, p-value = 0.2475\n",
       "alternative hypothesis: true location shift is not equal to 0\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "wilcox.test(value ~ group, subset = chem %in% 'ALP' & group %in% c('intact', 'vodka'),\n",
    "            data = biochemistry, paired = FALSE)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### ALT"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tWilcoxon rank sum test\n",
       "\n",
       "data:  value by group\n",
       "W = 83, p-value = 0.0115\n",
       "alternative hypothesis: true location shift is not equal to 0\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "wilcox.test(value ~ group, subset = chem %in% 'ALT' & group %in% c('intact', 'vodka'),\n",
    "            data = biochemistry, paired = FALSE)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### AST"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tWilcoxon rank sum test\n",
       "\n",
       "data:  value by group\n",
       "W = 32, p-value = 0.1903\n",
       "alternative hypothesis: true location shift is not equal to 0\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "wilcox.test(value ~ group, subset = chem %in% 'AST' & group %in% c('intact', 'vodka'),\n",
    "            data = biochemistry, paired = FALSE)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### LDH"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "\tWilcoxon rank sum test\n",
       "\n",
       "data:  value by group\n",
       "W = 11, p-value = 0.002089\n",
       "alternative hypothesis: true location shift is not equal to 0\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "wilcox.test(value ~ group, subset = chem %in% 'LDH' & group %in% c('intact', 'vodka'),\n",
    "            data = biochemistry, paired = FALSE)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "------"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "ferments <- c('ALP', 'ALT', 'AST', 'LDH')\n",
    "groups <- c('paracetamol', 'alcohol', 'vodka')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[1] \"paracetamol\"          \"ALP\"                  \"0.000129901058693628\"\n",
      "[1] \"paracetamol\"         \"ALT\"                 \"0.00684145575786443\"\n",
      "[1] \"paracetamol\"       \"AST\"               \"0.143140141592154\"\n",
      "[1] \"paracetamol\"          \"LDH\"                  \"0.000487128970101106\"\n",
      "[1] \"alcohol\"           \"ALP\"               \"0.630528913810648\"\n",
      "[1] \"alcohol\"              \"ALT\"                  \"0.000487128970101106\"\n",
      "[1] \"alcohol\"           \"AST\"               \"0.165493948775683\"\n",
      "[1] \"alcohol\" \"LDH\"     \"1\"      \n",
      "[1] \"vodka\"             \"ALP\"               \"0.247450691723138\"\n",
      "[1] \"vodka\"              \"ALT\"                \"0.0114962436943861\"\n",
      "[1] \"vodka\"            \"AST\"              \"0.19031587607439\"\n",
      "[1] \"vodka\"               \"LDH\"                 \"0.00208924202732252\"\n"
     ]
    }
   ],
   "source": [
    "for(group_ in groups){\n",
    "    for(ferment_ in ferments){\n",
    "        p_value <- wilcox.test(value ~ group, data = biochemistry, paired = FALSE,\n",
    "                               subset = chem %in% ferment_ & group %in% c('intact', group_))$p.value\n",
    "        print(c(group_, ferment_, p_value))\n",
    "    }\n",
    "}"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "R",
   "language": "R",
   "name": "ir"
  },
  "language_info": {
   "codemirror_mode": "r",
   "file_extension": ".r",
   "mimetype": "text/x-r-source",
   "name": "R",
   "pygments_lexer": "r",
   "version": "3.3.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}

rats_masses.ipynb

rats_microbiology.ipynb