Skip to content

Umair_Hanif_Assignment_python_1 #24

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Umair_Hanif_Assignment_python_1 #24

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d339a7b
Assessment01_Umair_Hanif_Python
umairhanif00 Mar 17, 2017
ea8efa5
Umair_Hanif_Assignment_python_1
umairhanif00 Mar 20, 2017
6040adf
Umair_Hanif_Assignment_python_1
umairhanif00 Mar 20, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
208 changes: 208 additions & 0 deletions Assessment_01_Umair_Hanif.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,208 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"import pandas\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"\n",
"df = pandas.read_csv(\"C:/Users/umair.hanif/Desktop/Learning Outcomes/Updated Dataset/Updated Dataset/Dataset/chronic_kidney_disease_updated.csv\")\n"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['age', 'bp', 'sg', 'al', 'su', 'rbc', 'pc', 'pcc', 'ba', 'bgr', 'bu', 'sc', 'sod', 'pot', 'hemo', 'pcv', 'wbcc', 'rbcc', 'htn', 'dm', 'cad', 'appet', 'pe', 'ane', 'class']\n",
" age bp sg al su rbc pc pcc ba bgr ... \\\n",
"2 7 50 1.020 4 0 NaN normal notpresent notpresent NaN ... \n",
"3 62 80 1.010 2 3 normal normal notpresent notpresent 423 ... \n",
"4 48 70 1.005 4 0 normal abnormal present notpresent 117 ... \n",
"5 51 80 1.010 2 0 normal normal notpresent notpresent 106 ... \n",
"6 60 90 1.015 3 0 NaN NaN notpresent notpresent 74 ... \n",
"\n",
" pcv wbcc rbcc htn dm cad appet pe ane class \n",
"2 38 6000 NaN no no no good no no ckd \n",
"3 31 7500 NaN no yes no poor no yes ckd \n",
"4 32 6700 3.9 yes no no poor yes yes ckd \n",
"5 35 7300 4.6 no no no good no no ckd \n",
"6 39 7800 4.4 yes yes no good yes no ckd \n",
"\n",
"[5 rows x 25 columns]\n",
"['yes' 'no' nan]\n",
"['yes' 'no' 'nan']\n",
" pc al\n",
"3 normal 2\n",
"4 abnormal 4\n",
"5 normal 2\n",
"6 nan 3\n",
"7 normal 0\n",
"8 abnormal 2\n",
"9 abnormal 3\n",
"10 abnormal 2\n",
"11 abnormal 2\n",
"12 abnormal 3\n",
"13 normal 3\n",
"14 nan nan\n",
"15 abnormal 3\n",
"16 normal 3\n",
"17 normal 2\n",
"18 nan nan\n",
"19 normal 0\n",
"20 abnormal 1\n",
"21 abnormal 2\n",
"22 nan nan\n",
"23 abnormal 4\n",
"24 normal 0\n",
"25 abnormal 4\n",
"26 normal 0\n",
"27 normal 0\n",
"28 abnormal 3\n",
"29 nan 1\n",
"30 abnormal 1\n",
"31 nan nan\n",
"32 abnormal 3\n",
".. ... ...\n",
"371 normal 0\n",
"372 normal 0\n",
"373 normal 0\n",
"374 normal 0\n",
"375 normal 0\n",
"376 normal 0\n",
"377 normal 0\n",
"378 normal 0\n",
"379 normal 0\n",
"380 normal 0\n",
"381 normal 0\n",
"382 nan 0\n",
"383 normal 0\n",
"384 normal 0\n",
"385 normal 0\n",
"386 normal 0\n",
"387 normal 0\n",
"388 normal 0\n",
"389 normal 0\n",
"390 normal 0\n",
"391 normal 0\n",
"392 normal 0\n",
"393 normal 0\n",
"394 normal 0\n",
"395 normal 0\n",
"396 normal 0\n",
"397 normal 0\n",
"398 normal 0\n",
"399 normal 0\n",
"400 normal 0\n",
"\n",
"[398 rows x 2 columns]\n",
"180.0\n"
]
}
],
"source": [
"#print column names\n",
"print(list(df) )\n",
"\n",
"#print first 5 rows\n",
"print(df.head())\n",
"\n",
"df.drop(df.index[[0]], inplace=True)\n",
"\n",
"print(df.dm.unique() )\n",
"\n",
"def replace(tup, df):\n",
" for i in tup:\n",
" df.replace(to_replace=i, value=np.nan, inplace=True)\n",
" \n",
"def cleandf(df):\n",
" df=df.applymap(lambda x: str(x).strip())\n",
" return df\n",
" \n",
"df=cleandf(df)\n",
" \n",
"replace(( \"\\t\", \" \", \"?\"), df)\n",
"\n",
"print(df.dm.unique() )\n",
"\n",
"\n",
"numeric_columns= ['age', 'bp', 'bgr', 'bu', 'sc', 'sod', 'pot', 'hemo', 'pcv', 'wbcc', 'rbcc']\n",
"for i in numeric_columns:\n",
" df[i] = pandas.to_numeric(df[i], errors='coerce')\n",
"\n",
"\n",
"print(df[['pc','al']])\n",
"\n",
"df.rename(columns={'class': 'Class'}, inplace=True)\n",
"ckd=df[df.Class=='ckd']\n",
"\n",
"normal_count=(len(ckd[ckd.rbc=='normal'].index))\n",
"abnormal_count=(len(ckd[ckd.rbc=='abnormal'].index))\n",
"\n",
"ckd['rbc'].value_counts().plot(kind='bar')\n",
"\n",
"print(ckd['bp'].max())\n",
"\n",
"\n",
"df.to_csv(path_or_buf=\"C:/Users/umair.hanif/Desktop/Learning Outcomes/Python Codes/clean_chronic_kidney_disease.csv\")\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAEhCAYAAABx6WukAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n7v8B9erMBMVRUWkAAAAASUVORK5CYII=\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x1981c2b5e80>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plt.style.use('ggplot')\n",
"plt.show()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.6.0"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Loading