Plt,_seaborn
import csv
f=open('seoul.csv')
data=csv.reader(f)
header=next(data)
max_temp=-999
max_date=''
for row in data:
if row[-1] == '' :
row[-1] = -999
row[-1] = float(row[-1])
if max_temp < row[-1] :
max_date = row[0]
max_temp = row[-1]
f.close()
print('기상 관측 이래 서울의 최고 기온이 가장 높았던 날은',max_date+'로',max_temp,'도 였습니다.')
기상 관측 이래 서울의 최고 기온이 가장 높았던 날은 2018-08-01로 39.6 도 였습니다.
import matplotlib.pyplot
import matplotlib.pyplot as plt
import matplotlib.pyplot as plt
plt.plot([10,20,30,40])
plt.show()
import matplotlib.pyplot as plt
plt.plot([1,2,3,4],[12,43,25,15])
plt.show
<function matplotlib.pyplot.show(close=None, block=None)>
import matplotlib.pyplot as plt
plt.title('plotting')
plt.plot([10,20,30,40])
plt.show()
import matplotlib.pyplot as plt
plt.title('legend')
plt.plot([10,20,30,40],label='asc')
plt.plot([40,30,20,10],label='desc')
plt.legend()
plt.show()
import matplotlib.pyplot as plt
plt.title('color') # 제목 설정
#그래프 그리기
plt.plot([10,20,30,40],color='skyblue',label='asc')
plt.plot([40,30,20,10],color='pink',label='desc')
plt.legend()
plt.show()
import matplotlib.pyplot as plt
plt.title('linestyle') # 제목 설정
#빨간색 dashed 그래프
plt.plot([10,20,30,40],color='r',linestyle='--',label='dashed')
#초록색 dotted 그래프
plt.plot([40,30,20,10],color='g',ls=':',label='dotted')
plt.legend()
plt.show()
import matplotlib.pyplot as plt
plt.title('marker') # 제목 설정
#빨간색 dashed 그래프
plt.plot([10,20,30,40],'r.',label='circle')
#초록색 삼각형 마커
plt.plot([40,30,20,10],'g^',label='triangle up')
plt.legend()
plt.show()
plt.plot(result,'r')
plt.figure(figsize=(10,2))
plt.show()
<Figure size 720x144 with 0 Axes>
s= 'hello pyhton'
print(s.split())
['hello', 'pyhton']
date='1907-10-01'
print(date.split('-'))
print(date.split('-')[0])
print(date.split('-')[1])
print(date.split('-')[2])
['1907', '10', '01']
1907
10
01
for row in data :
if row[-1] !='' :
if row[0].split('-')[1]=='08' :
result.append(float(row[-1]))
plt.plot(result,'hotpink')
plt.show
<function matplotlib.pyplot.show(close=None, block=None)>
for row in data :
if row[-1] !='' :
if row[0].split('-')[1]=='02' and row[0].split('-')[2]=='14':
result.append(float(row[-1]))
import csv
import matplotlib.pyplot as plt
f=open('seoul.csv')
data=csv.reader(f)
next(data)
high= []
low= []
for row in data :
if row[-1]!='' and row[-2] !='':
if 1983 <= int(row[0].split('-')[0]) :
if row[0].split('-')[1] == '02' and row[0].split('-')[2]=='14' :
high.append(float(row[-1]))
low.append(float(row[-2]))
plt.rc('font',family='Malgun Gothic')
plt.rcParams['axes.unicode_minus'] =False
plt.title('내 생일의 기온 변화 그래프')
plt.plot(high,'hotpink',label='high')
plt.plot(low,'skyblue',label='low')
plt.legend()
plt.show()
import matplotlib.pyplot as plt
plt.hist([1,1,2,3,4,5,6,6,7,8,10])
plt.show
<function matplotlib.pyplot.show(close=None, block=None)>
import random
print(random.randint(1,6))
5
import random
dice=[]
for i in range(5) :
dice.append(random.randint(1,6))
print(dice)
[3, 5, 4, 3, 3]
import matplotlib.pyplot as plt
plt.hist(dice,bins=6)
plt.show
<function matplotlib.pyplot.show(close=None, block=None)>
import random
dice=[]
for i in range(100) :
dice.append(random.randint(1,6))
print(dice)
[5, 4, 5, 3, 5, 6, 3, 5, 4, 5, 3, 3, 2, 1, 5, 4, 5, 4, 2, 3, 1, 5, 1, 5, 6, 2, 4, 4, 4, 6, 3, 3, 3, 4, 1, 1, 3, 5, 3, 5, 1, 4, 3, 5, 4, 5, 5, 2, 6, 3, 2, 1, 5, 3, 1, 2, 6, 1, 3, 3, 3, 4, 4, 6, 5, 2, 1, 1, 1, 5, 3, 5, 3, 5, 2, 6, 1, 2, 1, 2, 5, 1, 2, 2, 3, 2, 1, 2, 5, 2, 1, 3, 6, 1, 3, 1, 5, 2, 5, 1]
import matplotlib.pyplot as plt
plt.hist(dice,bins=6)
plt.show
<function matplotlib.pyplot.show(close=None, block=None)>
#기온 그래프를 히스토 그램으로 표현하기
import csv
import matplotlib.pyplot as plt
f=open('seoul.csv')
data=csv.reader(f)
next(data)
result=[]
for row in data :
if row[-1] !='' :
result.append(float(row[-1]))
plt.hist(result,bins=100,color='r')
plt.show
<function matplotlib.pyplot.show(close=None, block=None)>
# sns 를 이용하여 기온 그래프를 히스토 그램으로 표현하기
import seaborn as sns
import pandas as pd
import matplotlib.pyplot as plt
seoul=pd.read_csv("G:/seoul.csv",engine='python')
seoul
| 날짜 | 지점 | 평균기온(℃) | 최저기온(℃) | 최고기온(℃) | |
|---|---|---|---|---|---|
| 0 | 1907-10-01 | 108 | 13.5 | 7.9 | 20.7 |
| 1 | 1907-10-02 | 108 | 16.2 | 7.9 | 22.0 |
| 2 | 1907-10-03 | 108 | 16.2 | 13.1 | 21.3 |
| 3 | 1907-10-04 | 108 | 16.5 | 11.2 | 22.0 |
| 4 | 1907-10-05 | 108 | 17.6 | 10.9 | 25.4 |
| ... | ... | ... | ... | ... | ... |
| 40216 | 2019-01-13 | 108 | 1.2 | -3.0 | 7.6 |
| 40217 | 2019-01-14 | 108 | 1.4 | -2.4 | 5.3 |
| 40218 | 2019-01-15 | 108 | -1.7 | -7.2 | 2.6 |
| 40219 | 2019-01-16 | 108 | -5.2 | -10.1 | -1.1 |
| 40220 | 2019-01-17 | 108 | -0.3 | -3.2 | 4.0 |
40221 rows × 5 columns
sns.distplot(seoul["평균기온(℃)"])
E:\anaconda3\lib\site-packages\seaborn\distributions.py:2551: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)
<AxesSubplot:xlabel='평균기온(℃)', ylabel='Density'>
#8월 평균기온
import csv
import matplotlib.pyplot as plt
f=open('seoul.csv')
data=csv.reader(f)
next(data)
aug=[]
for row in data :
month = row[0].split('-')[1]
if row[-1] !='' :
if month =='08':
aug.append(float(row[-1]))
plt.hist(aug,bins=100,color='r')
plt.show
<function matplotlib.pyplot.show(close=None, block=None)>
#sns 이용 8월 평균 기온
import datetime
print(seoul)
print(seoul.index)
print(seoul.columns)
#열 이름을 변경
seoul.rename(columns={'날짜':'date', '지점':'point', '평균기온(℃)':'average','최저기온(℃)':'low','최고기온(℃)':'high'}, inplace=True)
print(seoul)
날짜 지점 평균기온(℃) 최저기온(℃) 최고기온(℃)
0 1907-10-01 108 13.5 7.9 20.7
1 1907-10-02 108 16.2 7.9 22.0
2 1907-10-03 108 16.2 13.1 21.3
3 1907-10-04 108 16.5 11.2 22.0
4 1907-10-05 108 17.6 10.9 25.4
... ... ... ... ... ...
40216 2019-01-13 108 1.2 -3.0 7.6
40217 2019-01-14 108 1.4 -2.4 5.3
40218 2019-01-15 108 -1.7 -7.2 2.6
40219 2019-01-16 108 -5.2 -10.1 -1.1
40220 2019-01-17 108 -0.3 -3.2 4.0
[40221 rows x 5 columns]
RangeIndex(start=0, stop=40221, step=1)
Index(['날짜', '지점', '평균기온(℃)', '최저기온(℃)', '최고기온(℃)'], dtype='object')
date point average low high
0 1907-10-01 108 13.5 7.9 20.7
1 1907-10-02 108 16.2 7.9 22.0
2 1907-10-03 108 16.2 13.1 21.3
3 1907-10-04 108 16.5 11.2 22.0
4 1907-10-05 108 17.6 10.9 25.4
... ... ... ... ... ...
40216 2019-01-13 108 1.2 -3.0 7.6
40217 2019-01-14 108 1.4 -2.4 5.3
40218 2019-01-15 108 -1.7 -7.2 2.6
40219 2019-01-16 108 -5.2 -10.1 -1.1
40220 2019-01-17 108 -0.3 -3.2 4.0
[40221 rows x 5 columns]
seoul['date']=pd.to_datetime(seoul['date'])
seoul['date']
0 1907-10-01
1 1907-10-02
2 1907-10-03
3 1907-10-04
4 1907-10-05
...
40216 2019-01-13
40217 2019-01-14
40218 2019-01-15
40219 2019-01-16
40220 2019-01-17
Name: date, Length: 40221, dtype: datetime64[ns]
seoul['year'] = seoul['date'].dt.year
seoul['month'] = seoul['date'].dt.month
seoul['day'] = seoul['date'].dt.day
seoul
| date | point | average | low | high | year | month | day | |
|---|---|---|---|---|---|---|---|---|
| 0 | 1907-10-01 | 108 | 13.5 | 7.9 | 20.7 | 1907 | 10 | 1 |
| 1 | 1907-10-02 | 108 | 16.2 | 7.9 | 22.0 | 1907 | 10 | 2 |
| 2 | 1907-10-03 | 108 | 16.2 | 13.1 | 21.3 | 1907 | 10 | 3 |
| 3 | 1907-10-04 | 108 | 16.5 | 11.2 | 22.0 | 1907 | 10 | 4 |
| 4 | 1907-10-05 | 108 | 17.6 | 10.9 | 25.4 | 1907 | 10 | 5 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 40216 | 2019-01-13 | 108 | 1.2 | -3.0 | 7.6 | 2019 | 1 | 13 |
| 40217 | 2019-01-14 | 108 | 1.4 | -2.4 | 5.3 | 2019 | 1 | 14 |
| 40218 | 2019-01-15 | 108 | -1.7 | -7.2 | 2.6 | 2019 | 1 | 15 |
| 40219 | 2019-01-16 | 108 | -5.2 | -10.1 | -1.1 | 2019 | 1 | 16 |
| 40220 | 2019-01-17 | 108 | -0.3 | -3.2 | 4.0 | 2019 | 1 | 17 |
40221 rows × 8 columns
#8월 특정 월만 추출
seoul_aug=seoul[seoul['month'] == 8]
seoul_aug
sns.distplot(seoul_aug["high"],kde=False,rug=True)
E:\anaconda3\lib\site-packages\seaborn\distributions.py:2551: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
warnings.warn(msg, FutureWarning)
E:\anaconda3\lib\site-packages\seaborn\distributions.py:2055: FutureWarning: The `axis` variable is no longer used and will be removed. Instead, assign variables directly to `x` or `y`.
warnings.warn(msg, FutureWarning)
<AxesSubplot:xlabel='high'>
#1월과 8월데이터 추출
seoul18=seoul[seoul['month'].isin([1,8])]
seoul18['month'].value_counts()
seoul18
| date | point | average | low | high | year | month | day | |
|---|---|---|---|---|---|---|---|---|
| 92 | 1908-01-01 | 108 | -5.9 | -9.1 | -1.3 | 1908 | 1 | 1 |
| 93 | 1908-01-02 | 108 | -7.7 | -13.9 | -3.0 | 1908 | 1 | 2 |
| 94 | 1908-01-03 | 108 | -6.2 | -10.8 | -2.9 | 1908 | 1 | 3 |
| 95 | 1908-01-04 | 108 | -7.5 | -12.8 | -1.7 | 1908 | 1 | 4 |
| 96 | 1908-01-05 | 108 | -4.8 | -11.3 | -0.1 | 1908 | 1 | 5 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 40216 | 2019-01-13 | 108 | 1.2 | -3.0 | 7.6 | 2019 | 1 | 13 |
| 40217 | 2019-01-14 | 108 | 1.4 | -2.4 | 5.3 | 2019 | 1 | 14 |
| 40218 | 2019-01-15 | 108 | -1.7 | -7.2 | 2.6 | 2019 | 1 | 15 |
| 40219 | 2019-01-16 | 108 | -5.2 | -10.1 | -1.1 | 2019 | 1 | 16 |
| 40220 | 2019-01-17 | 108 | -0.3 | -3.2 | 4.0 | 2019 | 1 | 17 |
6806 rows × 8 columns
#1월 8월 그래프 그리기
sns.distplot(data=seoul18,x="high",hue="month")
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-132-f005587ed421> in <module>
1 #1월 8월 그래프 그리기
2
----> 3 sns.distplot(data=seoul18,x="high",hue="month")
TypeError: distplot() got an unexpected keyword argument 'data'
sns.distplot(seoul["high"][seoul["month"]==1], kde=False,label='Jan')
sns.distplot(seoul["high"][seoul["month"]==8], kde=False, color="r",label='Aug')
plt.legend()
plt.figure(figsize=(30,10))
plt.show()
<Figure size 2160x720 with 0 Axes>
import warnings
!pip install warnings
ERROR: Could not find a version that satisfies the requirement warnings (from versions: none)
ERROR: No matching distribution found for warnings
import warnings
warnings.filterwarnings('ignore')
sns.distplot(seoul["high"][seoul["month"]==8], kde=False,label='Aug')
<AxesSubplot:xlabel='high'>
#기온데이터를 상자 그림으로 표현하기
import matplotlib.pyplot as plt
import random
result=[]
for i in range(13) :
result.append(random.randint(1,1000))
print(sorted(result))
plt.boxplot(result)
plt.show
[53, 196, 219, 232, 335, 395, 409, 409, 602, 604, 833, 883, 967]
<function matplotlib.pyplot.show(close=None, block=None)>
#최대기온 그래프를 상자 으로 표현하기
import csv
import matplotlib.pyplot as plt
f=open('seoul.csv')
data=csv.reader(f)
next(data)
result=[]
for row in data :
if row[-1] !='' :
result.append(float(row[-1]))
plt.boxplot(result)
plt.show()
sns.boxplot(x="month",y="high",data=seoul18)
<AxesSubplot:xlabel='month', ylabel='high'>
sns.boxplot(x="month",y="high",data=seoul)
<AxesSubplot:xlabel='month', ylabel='high'>
#8월 일별 기온 데이터를 상자 그림으로 그리기
sns.boxplot(x=seoul["day"][seoul["month"]==8],y="high",data=seoul)
plt.figure(figsize=(15,4))
plt.show()
<Figure size 1080x288 with 0 Axes>
git add
File "<ipython-input-1-3d50770d72e9>", line 1
git add
^
SyntaxError: invalid syntax
댓글남기기