Пишем модуль прогнозирования погоды на Python.

Импорт необходимых библиотек

import matplotlib.pyplot as plt
import seaborn as sns
import scipy
import re
import missingno as mso
from scipy import stats
from scipy.stats import ttest_ind
from scipy.stats import pearsonr
from sklearn.preprocessing import StandardScaler,LabelEncoder
from sklearn.model_selection import train_test_split 
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.ensemble import GradientBoostingClassifier
from xgboost import XGBClassifier
from sklearn.metrics import accuracy_score,confusion_matrix,classification_report
import pandas as pd

Чтение CSV-файла

data=pd.read_csv("/content/seattle-weather.csv")
data.head()

Форма данных

data.shape

(1461, 6)

import warnings
warnings.filterwarnings('ignore')
sns.countplot("weather",data=data,palette='hls')

countrain=len(data[data.weather=='rain'])
countsun=len(data[data.weather=='sun'])
countdrizzle=len(data[data.weather=='drizzle'])
countsnow=len(data[data.weather=='snow'])
countfog=len(data[data.weather=='fog'])
print('percent of rain:{:2f}%'.format((countrain/(len(data.weather))*100)))
print('percent of sun:{:2f}%'.format((countsun/(len(data.weather))*100)))
print('percent of drizzle:{:2f}%'.format((countdrizzle/(len(data.weather))*100)))
print('percent of snow:{:2f}%'.format((countsnow/(len(data.weather))*100)))
print('percent of fog:{:2f}%'.format((countfog/(len(data.weather))*100)))

data[['precipitation','temp_max','temp_min','wind']].describe()

sns.set(style='darkgrid')
fig,axs=plt.subplots(2,2,figsize=(10,8))
sns.histplot(data=data,x='precipitation',kde=True,ax=axs[0,0],color='green')
sns.histplot(data=data,x='temp_max',kde=True,ax=axs[0,1],color='red')
sns.histplot(data=data,x='temp_min',kde=True,ax=axs[1,0],color='blue')
sns.histplot(data=data,x='wind',kde=True,ax=axs[1,1],color='orange')

sns.set(style='darkgrid')
fig,axs=plt.subplots(2,2,figsize=(10,8))
sns.violinplot(data=data,x='precipitation',kde=True,ax=axs[0,0],color='green')
sns.violinplot(data=data,x='temp_max',kde=True,ax=axs[0,1],color='red')
sns.violinplot(data=data,x='temp_min',kde=True,ax=axs[1,0],color='blue')
sns.violinplot(data=data,x='wind',kde=True,ax=axs[1,1],color='orange')

plt.figure(figsize=(12,6))
sns.boxplot('precipitation','weather',data=data,palette='YlOrBr')

plt.figure(figsize=(12,6))
sns.boxplot('temp_max','weather',data=data,palette='inferno')

plt.figure(figsize=(12,6))
sns.boxplot('wind','weather',data=data,palette='YlOrBr')

plt.figure(figsize=(12,6))
sns.boxplot('temp_min','weather',data=data,palette='YlOrBr')

plt.figure(figsize=(12,6))
sns.heatmap(data.corr(),annot=True,cmap='coolwarm')

data.plot("precipitation",'temp_max',style='o')
print('pearsons correlation: ',data['precipitation'].corr(data['temp_max']))
print('T test and P value: ',stats.ttest_ind(data['precipitation'],data['temp_max']))

Корреляция Пирсона: -0,22855481643297046
T-тест и значение P: Ttest_indResult(statistic=-51.60685279531918, pvalue=0.0)

data.plot("wind",'temp_max',style='o')
print('pearsons correlation: ',data['wind'].corr(data['temp_max']))
print('T test and P value: ',stats.ttest_ind(data['wind'],data['temp_max']))

Корреляция Пирсона: -0,16485663487495486
T-тест и значение P: Ttest_indResult(statistic=-67.3601643301846, pvalue=0.0)

 data.plot('temp_max','temp_min',style='o')

data.isna().sum()

plt.figure(figsize=(12,6))
axz=plt.subplot(1,2,2)
mso.bar(data.drop(['date'],axis=1),ax=axz,fontsize=12)

data=data.drop(['date'],axis=1)

Q1=data.quantile(0.25)
Q3=data.quantile(0.75)
IQR=Q3-Q1
data=data[~((data<(Q1-1.5*IQR))|(data>(Q3+1.5*IQR))).any(axis=1)]

import numpy as np
data.precipitation=np.sqrt(data.precipitation)
data.wind=np.sqrt(data.wind)

sns.set(style='darkgrid')
fig, axs=plt.subplots(2,2,figsize=(10,8))
sns.histplot(data=data,x="precipitation",kde=True,ax=axs[0,0],color='green')
sns.histplot(data=data,x="temp_max",kde=True,ax=axs[0,1],color='red')
sns.histplot(data=data,x="temp_min",kde=True,ax=axs[1,0],color='blue')
sns.histplot(data=data,x="wind",kde=True,ax=axs[1,1],color='orange')

data.head()

lc=LabelEncoder()
data['weather']=lc.fit_transform(data['weather'])

data.head()

x=((data.loc[:,data.columns!='weather']).astype(int)).values[:,0:]
y=data['weather'].values

data.weather.unique()

x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.1,random_state=2)

knn=KNeighborsClassifier()
knn.fit(x_train,y_train)
print('KNN accuracy:{:.2f}%'.format(knn.score(x_test,y_test)*100))

svm=SVC()
svm.fit(x_train,y_train)
print('SVM accuracy:{:.2f}%'.format(svm.score(x_test,y_test)*100))

gbc=GradientBoostingClassifier(subsample=0.5,n_estimators=450,max_depth=5,max_leaf_nodes=25)
gbc.fit(x_train,y_train)
print('GBC accuracy:{:.2f}%'.format(gbc.score(x_test,y_test)*100))

import warnings
warnings.filterwarnings('ignore')
xgb=XGBClassifier()
xgb.fit(x_train,y_train)
print('XGB accuracy:{:.2f}%'.format(xgb.score(x_test,y_test)*100))

input=[[1.140175,8.9,2.8,2.469818]]
ot=xgb.predict(input)
print('the weather is:')
if(ot==0):
  print('Drizzle')
elif (ot==1):
  print('fogg')
elif (ot==2):
  print('rain')
elif (ot==3):
  print('snow')
else:
  print('sun')

import pickle
file = 'model.pkl'
pickle.dump(xgb, open(file, 'wb'))