Skip to content

Poterek exercise 9 #9

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
mpoterek wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Poterek exercise 9 #9

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
55 changes: 55 additions & 0 deletions ex9solutions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,55 @@
#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Sat Nov 3 14:04:49 2018

@author: mlpoterek
"""

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
import pylab

#Problem 1
location = r'/Users/mlpoterek/Biocomp/ICB_EX9/pred_obs.csv'
df = pd.read_csv(location, encoding="utf-8-sig")

plt.plot("Predicted", "Observed",'bo', data = df)

#To generate the trendline
z = np.polyfit(df['Predicted'], df['Observed'], 1)
p = np.poly1d(z)
pylab.plot(df['Predicted'],p(df['Predicted']),"r--")

#To add labels
plt.ylabel('Observed Cases')
plt.xlabel('Predicted Cases')
plt.show

#Problem 2
location1 = r'/Users/mlpoterek/Biocomp/ICB_EX9/data.txt'
df1 = pd.read_csv(location1, encoding="utf-8-sig")

north_df = df1[df1["region"]== "north"]
south_df = df1[df1["region"]== "south"]
east_df = df1[df1["region"]== "east"]
west_df = df1[df1["region"]== "west"]

#Bar graph of means
plt.bar(("north", "south", "east", "west"), (north_df['observations'].mean(), south_df['observations'].mean(), east_df['observations'].mean(), west_df['observations'].mean()))
plt.ylabel('Population Mean')
plt.xlabel('Region')
plt.show

#Scatter plot of all observations
sns.stripplot(x='region', y='observations', data=df1, jitter=True, alpha = .4)
sns.despine()

#The bar graph shows all four regions to be very similar, as each has
#essentially the same population mean. The scatterplot, though, reveals that
#observations from the north region are clustered around the mean, that
#observations from the east and west regions are relatively consistently
#spread out around the mean, and that the south region's data is clustered into
#two distinct groups: one far above the mean and one far below.
187 changes: 187 additions & 0 deletions pred_obs.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,187 @@
Observed,Predicted
19,13
5,6
1,3
13,20
0,1
2,3
1,1
2,1
3,1
7,3
0,1
2,1
1,2
0,4
0,2
1,1
1,0
0,1
2,1
2,0
2,0
1,0
0,0
2,0
0,0
0,0
1,0
0,0
0,0
1,0
0,0
0,0
4,0
1,0
0,0
1,0
0,0
0,0
0,0
3,0
0,0
0,0
1,0
0,0
0,0
0,0
0,0
1,0
0,0
0,0
3,3
0,1
0,1
6,5
0,0
0,1
0,0
0,0
0,0
0,1
0,0
0,0
2,0
0,1
0,0
1,0
1,0
1,0
0,0
0,0
0,0
0,0
0,0
0,0
0,0
0,0
2,0
0,0
0,0
0,0
0,0
0,0
0,0
1,0
0,0
0,0
2,0
2,0
10,7
2,3
4,3
10,9
0,1
5,2
0,1
1,0
2,0
1,1
1,0
3,1
0,1
0,2
0,1
3,1
3,0
0,1
1,1
0,0
1,0
0,0
3,0
0,0
0,0
0,0
1,0
1,0
17,19
0,5
3,4
7,11
5,3
1,4
0,2
0,1
1,1
6,2
1,1
4,2
1,1
0,3
0,1
2,1
1,1
3,1
1,1
1,0
6,9
2,3
1,3
6,8
0,1
0,3
0,1
0,0
2,0
0,1
0,1
0,1
1,1
1,3
1,1
0,1
0,0
1,1
0,1
0,0
0,0
1,0
1,0
1,0
0,0
0,0
0,0
1,0
3,7
0,1
1,2
1,6
0,1
1,3
0,0
0,0
2,0
1,1
2,1
0,1
0,0
0,3
1,1
1,0
0,0
0,0
1,0
0,0
1,0
1,0