Skip to content

Docker Assignment submission #3

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
farooqrehman wants to merge 1 commit into
base: master
Choose a base branch
from
+531 −0
Open

Docker Assignment submission #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
13 changes: 13 additions & 0 deletions Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
FROM ipython/notebook

RUN pip install pandas
RUN pip install datetime

RUN mkdir /Docker_A3
WORKDIR /Docker_A3
RUN mkdir ./code_files ./data

COPY code_files/*.ipynb ./code_files/
COPY data/*.csv ./data

WORKDIR /Docker_A3/code_files
295 changes: 295 additions & 0 deletions code_files/Python_Assignment_02.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,295 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import datetime\n",
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"hospitaldata = pd.read_csv(r'D:\\DIH\\Assignments\\FarooqUrRehman_KCI_Python_Assignment2\\hospitaldata.csv')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"#Answer 1\n",
"hospitaldata = hospitaldata.rename(columns=lambda x: x.replace('.', ''))\n",
"print(hospitaldata.columns)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"#Answer 2\n",
"hospitaldata['WeekDay'] = pd.to_datetime(hospitaldata['Date']).dt.weekday_name\n",
"WeekDay_Counts=hospitaldata[['WeekDay','id']].groupby('WeekDay').agg('count')\n",
"WeekDay_Max = WeekDay_Counts['id'].max()\n",
"print(WeekDay_Counts[(WeekDay_Counts['id'] == WeekDay_Max)])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"#Answer 3\n",
"\n",
"Average_Age = hospitaldata.dropna(subset =['Age'])\n",
"Average_Age = Average_Age[(Average_Age['Age']!='-')]\n",
"Average_Age['Age_Years']=Average_Age['Age'].str.extract('(\\d+)').astype(int)\n",
"Average_Age['Age_Years']=np.where(Average_Age['Age'].str.contains('M') == True, Average_Age['Age_Years']/12.0, Average_Age['Age_Years'])\n",
"print(Average_Age['Age_Years'].mean())"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"#Answer 4\n",
"Children_Count = Average_Age[(Average_Age['Age_Years'] >=1) & (Average_Age['Age_Years'] <=12)]\n",
"print(Children_Count['Age_Years'].count())"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"#Answer 5\n",
"Gender_Procedure = hospitaldata.dropna(subset =['Sex'])\n",
"Gender_Procedure = Gender_Procedure.dropna(subset =['Procedure'])\n",
"Gender_Procedure = Gender_Procedure[(Gender_Procedure['Sex']!='-')]\n",
"Gender_Procedure['Sex']=Gender_Procedure['Sex'].str.replace(\"m\",\"M\")\n",
"Gender_Procedure['Sex']=Gender_Procedure['Sex'].str.replace(\"f\",\"F\")\n",
"print(Gender_Procedure.groupby('Sex')['Procedure'].value_counts().nlargest(2))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"#Answer 6\n",
"Doctor_Earnings = hospitaldata[(hospitaldata['ConsultingDoctor'].str.contains(\"Dr\")==True)]\n",
"print(Doctor_Earnings.groupby(\"ConsultingDoctor\")['AmountReceived'].max().nlargest(1))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"#Answer 7\n",
"Procedure_Earnings=hospitaldata.dropna(subset =['Procedure'])\n",
"Procedure_Earnings=hospitaldata.dropna(subset =['AmountReceived'])\n",
"print(Procedure_Earnings.groupby(\"Procedure\")['AmountReceived'].sum().nlargest(1))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"#Answer 8\n",
"VF = hospitaldata.dropna(subset =['Time'])\n",
"VF = VF[(VF['Time']!='-')]\n",
"#Visit_Frequency['AM_PM']=np.where(Average_Age['Time'].str.contains('PM') == True, \"PM\",\"AM\")\n",
"VF['VisitHour']=pd.to_datetime(VF['Time'])\n",
"VF['VisitHour']=VF['VisitHour'].dt.hour\n",
"VF1=VF[['VisitHour','id']]\n",
"VF1.groupby('VisitHour')['id'].count().nlargest(1)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"#Answer 9\n",
"VF['TimeBracket']= np.where((VF['VisitHour'] >=6) & (VF['VisitHour'] <12), \"Morning\",np.where((VF['VisitHour'] >=12) & (VF['VisitHour'] <16), \"Afternoon\",np.where((VF['VisitHour'] >=16) & (VF['VisitHour'] <19), \"Evening\",\"Night\")))\n",
"VF[['TimeBracket','VisitHour']]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"#Answer 10 & 11\n",
"VF2=VF[['id','Date']].groupby('id').count()\n",
"VF2[VF2['Date'] > 1]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"#Answer 11\n",
"VF2=VF[['id','Date']].groupby('id').count()\n",
"VF2[VF2['Date'] > 1]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Answer 12\n",
"Gender_Procedure2=Gender_Procedure[['id','Procedure','Date']].groupby(['id','Procedure']).count()\n",
"Gender_Procedure2[Gender_Procedure2['Date']>1]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Answer 13\n",
"Average_Age['Sex']=Average_Age['Sex'].str.replace(\"m\",\"M\")\n",
"Average_Age['Sex']=Average_Age['Sex'].str.replace(\"f\",\"F\")\n",
"Average_Age.groupby(\"Sex\")['Age_Years'].mean()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Answer 14\n",
"Gender_Procedure = Gender_Procedure.dropna(subset =['AmountBalance'])\n",
"Gender_Procedure = Gender_Procedure[(Gender_Procedure['AmountBalance']!=' - ')]\n",
"Gender_Procedure['AmountBalance1'] = Gender_Procedure['AmountBalance'].str.replace(',','')\n",
"Gender_Procedure['AmountBalance1'] = Gender_Procedure['AmountBalance1'].str.extract('(\\d+)').astype(float)\n",
"sum(Gender_Procedure['AmountBalance1'])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Answer 15\n",
"Consultation_Earnings=Procedure_Earnings[(Procedure_Earnings['Procedure'] == 'Consultation')]\n",
"print(sum(Consultation_Earnings['AmountReceived']))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Answer 16\n",
"Age_Charges_Cor = Average_Age.dropna(subset =['TotalCharges'])\n",
"Age_Charges_Cor = Age_Charges_Cor[(Age_Charges_Cor['TotalCharges']!='Cancelled')]\n",
"np.correlate(Age_Charges_Cor['Age_Years'],Age_Charges_Cor['TotalCharges'].str.extract('(\\d+)').astype(float))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Answer 17\n",
"Average_Age['Age_Group']= np.where((Average_Age['Age_Years'] <=15), \"1-15 Yrs\",np.where((Average_Age['Age_Years'] >15) & (Average_Age['Age_Years'] <=30), \"16-30 Yrs\",np.where((Average_Age['Age_Years'] >30) & (Average_Age['Age_Years'] <=45), \"31-45 Yrs\",\"Above 45 Yrs\")))\n",
"print(Average_Age.groupby('Age_Group')['id'].count())"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"# Answer 18\n",
"XRay_Scalling_Earnings=Procedure_Earnings[(Procedure_Earnings['Procedure'] == 'X Ray') | (Procedure_Earnings['Procedure'] == 'Scalling')]\n",
"print(sum(XRay_Scalling_Earnings['AmountReceived']))"
]
}
],
"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