Case Study (Problem Set 4) Solution

x
1
from pathlib import Path
2

3
path = Path('Harry_Potter.txt')
4
contents = path.read_text()
5

6
words = contents.split()
7
num_words = len(words)
8
x=f"The file {path} has about {num_words} words."
9

10
path = Path('Count_Words.txt')
11
path.write_text(x)

x
1
import matplotlib.pyplot as plt
2

3
def threepoints(z):
4
    x1=z[0][0]
5
    y1=z[0][1]
6
    x2=z[1][0]
7
    y2=z[1][1]
8
    y=z[2][1]
9
    x=z[2][0]
10
    if (x2-x1)*y-(y2-y1)*x-y1*x2+y2*x1==0:
11
        print('They lie on a straight line.')
12
    else:
13
        fig, ax= plt.subplots()
14
        ax.plot([z[0][0],z[1][0]],[z[0][1],z[1][1]])
15
        ax.plot([z[1][0],z[2][0]],[z[1][1],z[2][1]])
16
        ax.plot([z[0][0],z[2][0]],[z[0][1],z[2][1]])
17
        plt.show()
18
        
19
n=[[1,1],[1,2],[1,3]]
20
m=[[1,1],[1,3],[2,2]]
21
threepoints(n)
22
threepoints(m)

xxxxxxxxxx
1
from pathlib import Path
2
import csv
3

4
path = Path('midterm.csv')
5
lines = path.read_text().splitlines()
6

7
reader = csv.reader(lines)
8
header_row = next(reader)
9

10
rows = []
11
for row in reader:
12
    rows.append(row[1])
13

14
def transform(score):
15
  if score<=100 and score>=90:
16
    return 'A'
17
  elif score<90 and score>=80:
18
    return 'B'
19
  elif score<80 and score>=70:
20
    return 'C'
21
  elif score<70 and score>=60:
22
    return 'D'
23
  elif score<60:
24
    return 'F'
25
t = []
26
for yy in rows:
27
  t.append(transform(float(yy)))
28
c=[t.count('A'),t.count('B'),t.count('C'),t.count('D'),t.count('F')]
29
# Visualize the results.
30
import plotly.express as px
31

32
data = ['A', 'B', 'C', 'D', 'F']
33
fig = px.bar(x = data, y=c)
34
fig.write_html('midterm.html')

4.

x
1
from pathlib import Path
2
import json
3

4
path = Path('data.json')
5
contents = path.read_text(encoding='utf-8')
6
data = json.loads(contents)
7

8
fre = dict()
9
for cx in data:
10
    if cx[1] not in fre:
11
        fre[cx[1]] = 1
12
    else:
13
        fre[cx[1]]+=1
14
name = []
15
count =[]
16
for x, y in fre.items():
17
    name.append(x)
18
    count.append(y)
19

20
# Visualize the results.
21
import plotly.express as px
22

23
fig = px.bar(x=name,y=count)
24
fig.write_html('canteen.html')

5.

xxxxxxxxxx
1
import json
2
import matplotlib.pyplot as plt
3
from datetime import datetime
4
from pathlib import Path
5

6
path = Path('data.json')
7
contents = path.read_text(encoding='utf-8')
8
data = json.loads(contents)
9

10
fre=dict()
11
for cx in data:
12
    if cx[0] not in fre:
13
        if float(cx[2])<0:
14
            fre[cx[0]] = -float(cx[2])
15
    else: 
16
        if float(cx[2])<0:
17
            fre[cx[0]]=fre[cx[0]]-float(cx[2])
18
dates = [] 
19
consumption=[]
20
for x, y in fre.items():
21
    current_date = datetime.strptime(x, "%m/%d/%Y")
22
    dates.append(current_date.strftime('%m-%d-%Y'))
23
    consumption.append(y)
24

25
# Visualize the results.
26
plt.style.use('seaborn')
27
fig, ax = plt.subplots()
28
ax.plot(dates, consumption, c='red')
29
ax.set_title("Daily Consumption", fontsize=24)
30
ax.set_xlabel('dates', fontsize=16)
31
fig.autofmt_xdate()
32
ax.set_ylabel("Consumption", fontsize=16)
33
ax.tick_params(labelsize=16)
34

35
plt.show()

xxxxxxxxxx
1
import csv
2
from pathlib import Path
3
from matplotlib import pyplot as plt
4

5
path = Path('athlete_events.csv')
6
lines = path.read_text().splitlines()
7

8
reader = csv.reader(lines)
9
header_row = next(reader)
10
    
11
year=[]
12
for row in reader:
13
    if row[7]=="CHN" and row[10]=="Summer":
14
         year.append(row[9])
15

16
from itertools import groupby
17

18
year.sort()
19
count={}
20
for key, value in groupby(year):
21
    count[key]=len(list(value))
22
c=[];labels=[]
23
for x,y in count.items():
24
    c.append(x)
25
    labels.append(y)
26
    
27
# Visualize the results.
28
plt.style.use('seaborn')
29
fig, ax = plt.subplots()
30
ax.plot(c,labels, c='red')
31
ax.set_title("Number of Athletes in Summer Games (China)", fontsize=24)
32
ax.set_xlabel('year', fontsize=16)
33
fig.autofmt_xdate()
34
ax.set_ylabel("number", fontsize=16)
35
ax.tick_params(labelsize=16)
36

37
plt.show()