RNN第三周-天气预测

本周只复现了代码

>- ** 本文为[365天深度学习训练营](https://mp.weixin.qq.com/s/xLjALoOD8HPZcH563En8bQ) 中的学习记录博客**
>- ** 参考文章：第R3周：LSTM-火灾温度预测（训练营内部可读）**
>- ** 作者：[K同学啊](https://mp.weixin.qq.com/s/xLjALoOD8HPZcH563En8bQ)**

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import warnings
warnings.filterwarnings('ignore')

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Activation,Dropout
from tensorflow.keras.callbacks import EarlyStopping
from tensorflow.keras.layers import Dropout
from sklearn.metrics import classification_report,confusion_matrix
from sklearn.metrics import r2_score
from sklearn.metrics import mean_absolute_error , mean_absolute_percentage_error , mean_squared_error

data = pd.read_csv("D:/DeepLearning/weatherAUS.csv")
df   = data.copy()
data.head()

Date	Location	MinTemp	MaxTemp	Rainfall	Evaporation	Sunshine	WindGustDir	WindGustSpeed	WindDir9am	...	Humidity9am	Humidity3pm	Pressure9am	Pressure3pm	Cloud9am	Cloud3pm	Temp9am	Temp3pm	RainToday	RainTomorrow
0	2008-12-01	Albury	13.4	22.9	0.6	NaN	NaN	W	44.0	W	...	71.0	22.0	1007.7	1007.1	8.0	NaN	16.9	21.8	No	No
1	2008-12-02	Albury	7.4	25.1	0.0	NaN	NaN	WNW	44.0	NNW	...	44.0	25.0	1010.6	1007.8	NaN	NaN	17.2	24.3	No	No
2	2008-12-03	Albury	12.9	25.7	0.0	NaN	NaN	WSW	46.0	W	...	38.0	30.0	1007.6	1008.7	NaN	2.0	21.0	23.2	No	No
3	2008-12-04	Albury	9.2	28.0	0.0	NaN	NaN	NE	24.0	SE	...	45.0	16.0	1017.6	1012.8	NaN	NaN	18.1	26.5	No	No
4	2008-12-05	Albury	17.5	32.3	1.0	NaN	NaN	W	41.0	ENE	...	82.0	33.0	1010.8	1006.0	7.0	8.0	17.8	29.7	No	No

5 rows × 23 columns

data.describe()

MinTemp	MaxTemp	Rainfall	Evaporation	Sunshine	WindGustSpeed	WindSpeed9am	WindSpeed3pm	Humidity9am	Humidity3pm	Pressure9am	Pressure3pm	Cloud9am	Cloud3pm	Temp9am	Temp3pm
count	143975.000000	144199.000000	142199.000000	82670.000000	75625.000000	135197.000000	143693.000000	142398.000000	142806.000000	140953.000000	130395.00000	130432.000000	89572.000000	86102.000000	143693.000000	141851.00000
mean	12.194034	23.221348	2.360918	5.468232	7.611178	40.035230	14.043426	18.662657	68.880831	51.539116	1017.64994	1015.255889	4.447461	4.509930	16.990631	21.68339
std	6.398495	7.119049	8.478060	4.193704	3.785483	13.607062	8.915375	8.809800	19.029164	20.795902	7.10653	7.037414	2.887159	2.720357	6.488753	6.93665
min	-8.500000	-4.800000	0.000000	0.000000	0.000000	6.000000	0.000000	0.000000	0.000000	0.000000	980.50000	977.100000	0.000000	0.000000	-7.200000	-5.40000
25%	7.600000	17.900000	0.000000	2.600000	4.800000	31.000000	7.000000	13.000000	57.000000	37.000000	1012.90000	1010.400000	1.000000	2.000000	12.300000	16.60000
50%	12.000000	22.600000	0.000000	4.800000	8.400000	39.000000	13.000000	19.000000	70.000000	52.000000	1017.60000	1015.200000	5.000000	5.000000	16.700000	21.10000
75%	16.900000	28.200000	0.800000	7.400000	10.600000	48.000000	19.000000	24.000000	83.000000	66.000000	1022.40000	1020.000000	7.000000	7.000000	21.600000	26.40000
max	33.900000	48.100000	371.000000	145.000000	14.500000	135.000000	130.000000	87.000000	100.000000	100.000000	1041.00000	1039.600000	9.000000	9.000000	40.200000	46.70000

data.dtypes

Date              object
Location          object
MinTemp          float64
MaxTemp          float64
Rainfall         float64
Evaporation      float64
Sunshine         float64
WindGustDir       object
WindGustSpeed    float64
WindDir9am        object
WindDir3pm        object
WindSpeed9am     float64
WindSpeed3pm     float64
Humidity9am      float64
Humidity3pm      float64
Pressure9am      float64
Pressure3pm      float64
Cloud9am         float64
Cloud3pm         float64
Temp9am          float64
Temp3pm          float64
RainToday         object
RainTomorrow      object
dtype: object

data['Date'] = pd.to_datetime(data['Date'])
data['Date']

0        2008-12-01
1        2008-12-02
2        2008-12-03
3        2008-12-04
4        2008-12-05
            ...    
145455   2017-06-21
145456   2017-06-22
145457   2017-06-23
145458   2017-06-24
145459   2017-06-25
Name: Date, Length: 145460, dtype: datetime64[ns]

data['year']  = data['Date'].dt.year
data['Month'] = data['Date'].dt.month
data['day']   = data['Date'].dt.day

Date	Location	MinTemp	MaxTemp	Rainfall	Evaporation	Sunshine	WindGustDir	WindGustSpeed	WindDir9am	...	Pressure3pm	Cloud9am	Cloud3pm	Temp9am	Temp3pm	RainToday	RainTomorrow	year	Month	day
0	2008-12-01	Albury	13.4	22.9	0.6	NaN	NaN	W	44.0	W	...	1007.1	8.0	NaN	16.9	21.8	No	No	2008	12	1
1	2008-12-02	Albury	7.4	25.1	0.0	NaN	NaN	WNW	44.0	NNW	...	1007.8	NaN	NaN	17.2	24.3	No	No	2008	12	2
2	2008-12-03	Albury	12.9	25.7	0.0	NaN	NaN	WSW	46.0	W	...	1008.7	NaN	2.0	21.0	23.2	No	No	2008	12	3
3	2008-12-04	Albury	9.2	28.0	0.0	NaN	NaN	NE	24.0	SE	...	1012.8	NaN	NaN	18.1	26.5	No	No	2008	12	4
4	2008-12-05	Albury	17.5	32.3	1.0	NaN	NaN	W	41.0	ENE	...	1006.0	7.0	8.0	17.8	29.7	No	No	2008	12	5

5 rows × 26 columns

data.drop('Date',axis=1,inplace=True)

data.columns

Index(['Location', 'MinTemp', 'MaxTemp', 'Rainfall', 'Evaporation', 'Sunshine',
       'WindGustDir', 'WindGustSpeed', 'WindDir9am', 'WindDir3pm',
       'WindSpeed9am', 'WindSpeed3pm', 'Humidity9am', 'Humidity3pm',
       'Pressure9am', 'Pressure3pm', 'Cloud9am', 'Cloud3pm', 'Temp9am',
       'Temp3pm', 'RainToday', 'RainTomorrow', 'year', 'Month', 'day'],
      dtype='object')

plt.figure(figsize=(15,13))
# data.corr()表示了data中的两个变量之间的相关性
ax = sns.heatmap(data.corr(), square=True, annot=True, fmt='.2f')
ax.set_xticklabels(ax.get_xticklabels(), rotation=90)          
plt.show()

sns.set(style="darkgrid")
plt.figure(figsize=(4,3))
sns.countplot(x='RainTomorrow',data=data)

 

plt.figure(figsize=(4,3))
sns.countplot(x='RainToday',data=data)

x=pd.crosstab(data['RainTomorrow'],data['RainToday'])
x

RainToday	No	Yes
RainTomorrow
No	92728	16858
Yes	16604	14597

y=x/x.transpose().sum().values.reshape(2,1)*100
y

y.plot(kind="bar",figsize=(4,3),color=['#006666','#d279a6']);

 

x=pd.crosstab(data['Location'],data['RainToday']) 
# 获取每个城市下雨天数和非下雨天数的百分比
y=x/x.transpose().sum().values.reshape((-1, 1))*100
# 按每个城市的雨天百分比排序
y=y.sort_values(by='Yes',ascending=True )

color=['#cc6699','#006699','#006666','#862d86','#ff9966'  ]
y.Yes.plot(kind="barh",figsize=(15,20),color=color)

data.columns

 

Index(['Location', 'MinTemp', 'MaxTemp', 'Rainfall', 'Evaporation', 'Sunshine',
       'WindGustDir', 'WindGustSpeed', 'WindDir9am', 'WindDir3pm',
       'WindSpeed9am', 'WindSpeed3pm', 'Humidity9am', 'Humidity3pm',
       'Pressure9am', 'Pressure3pm', 'Cloud9am', 'Cloud3pm', 'Temp9am',
       'Temp3pm', 'RainToday', 'RainTomorrow', 'year', 'Month', 'day'],
      dtype='object')

plt.figure(figsize=(8,6))
sns.scatterplot(data=data,x='Pressure9am',y='Pressure3pm',hue='RainTomorrow');

plt.figure(figsize=(8,6))
sns.scatterplot(data=data,x='Humidity9am',y='Humidity3pm',hue='RainTomorrow');

 

 

plt.figure(figsize=(8,6))
sns.scatterplot(x='MaxTemp', y='MinTemp', data=data, hue='RainTomorrow');

 

# 每列中缺失数据的百分比
data.isnull().sum()/data.shape[0]*100

Location          0.000000
MinTemp           1.020899
MaxTemp           0.866905
Rainfall          2.241853
Evaporation      43.166506
Sunshine         48.009762
WindGustDir       7.098859
WindGustSpeed     7.055548
WindDir9am        7.263853
WindDir3pm        2.906641
WindSpeed9am      1.214767
WindSpeed3pm      2.105046
Humidity9am       1.824557
Humidity3pm       3.098446
Pressure9am      10.356799
Pressure3pm      10.331363
Cloud9am         38.421559
Cloud3pm         40.807095
Temp9am           1.214767
Temp3pm           2.481094
RainToday         2.241853
RainTomorrow      2.245978
year              0.000000
Month             0.000000
day               0.000000
dtype: float64

# 在该列中随机选择数进行填充
lst=['Evaporation','Sunshine','Cloud9am','Cloud3pm']
for col in lst:
    fill_list = data[col].dropna()
    data[col] = data[col].fillna(pd.Series(np.random.choice(fill_list, size=len(data.index))))

s = (data.dtypes == "object")
object_cols = list(s[s].index)
object_cols

['Location',
 'WindGustDir',
 'WindDir9am',
 'WindDir3pm',
 'RainToday',
 'RainTomorrow']

# inplace=True：直接修改原对象，不创建副本
# data[i].mode()[0] 返回频率出现最高的选项，众数

for i in object_cols:
    data[i].fillna(data[i].mode()[0], inplace=True)

t = (data.dtypes == "float64")
num_cols = list(t[t].index)
num_cols

['MinTemp',
 'MaxTemp',
 'Rainfall',
 'Evaporation',
 'Sunshine',
 'WindGustSpeed',
 'WindSpeed9am',
 'WindSpeed3pm',
 'Humidity9am',
 'Humidity3pm',
 'Pressure9am',
 'Pressure3pm',
 'Cloud9am',
 'Cloud3pm',
 'Temp9am',
 'Temp3pm']

# .median(), 中位数
for i in num_cols:
    data[i].fillna(data[i].median(), inplace=True)

data.isnull().sum()

Location         0
MinTemp          0
MaxTemp          0
Rainfall         0
Evaporation      0
Sunshine         0
WindGustDir      0
WindGustSpeed    0
WindDir9am       0
WindDir3pm       0
WindSpeed9am     0
WindSpeed3pm     0
Humidity9am      0
Humidity3pm      0
Pressure9am      0
Pressure3pm      0
Cloud9am         0
Cloud3pm         0
Temp9am          0
Temp3pm          0
RainToday        0
RainTomorrow     0
year             0
Month            0
day              0
dtype: int64

from sklearn.preprocessing import LabelEncoder

label_encoder = LabelEncoder()
for i in object_cols:
    data[i] = label_encoder.fit_transform(data[i])

X = data.drop(['RainTomorrow','day'],axis=1).values
y = data['RainTomorrow'].values

X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.25,random_state=101)

scaler = MinMaxScaler()
scaler.fit(X_train)
X_train = scaler.transform(X_train)
X_test  = scaler.transform(X_test)

from tensorflow.keras.optimizers import Adam

model = Sequential()
model.add(Dense(units=24,activation='tanh',))
model.add(Dense(units=18,activation='tanh'))
model.add(Dense(units=23,activation='tanh'))
model.add(Dropout(0.5))
model.add(Dense(units=12,activation='tanh'))
model.add(Dropout(0.2))
model.add(Dense(units=1,activation='sigmoid'))

optimizer = tf.keras.optimizers.Adam(learning_rate=1e-4)

model.compile(loss='binary_crossentropy',
              optimizer=optimizer,
              metrics="accuracy")

early_stop = EarlyStopping(monitor='val_loss', 
                           mode='min',
                           min_delta=0.001, 
                           verbose=1, 
                           patience=25,
                           restore_best_weights=True)

model.fit(x=X_train, 
          y=y_train, 
          validation_data=(X_test, y_test), verbose=1,
          callbacks=[early_stop],
          epochs = 10,
          batch_size = 32
)

Epoch 1/10
3410/3410 [==============================] - 11s 2ms/step - loss: 0.4621 - accuracy: 0.7971 - val_loss: 0.3905 - val_accuracy: 0.8301
Epoch 2/10
3410/3410 [==============================] - 8s 2ms/step - loss: 0.3989 - accuracy: 0.8307 - val_loss: 0.3805 - val_accuracy: 0.8353
Epoch 3/10
3410/3410 [==============================] - 8s 2ms/step - loss: 0.3908 - accuracy: 0.8342 - val_loss: 0.3775 - val_accuracy: 0.8366
Epoch 4/10
3410/3410 [==============================] - 8s 2ms/step - loss: 0.3870 - accuracy: 0.8363 - val_loss: 0.3752 - val_accuracy: 0.8375
Epoch 5/10
3410/3410 [==============================] - 8s 2ms/step - loss: 0.3846 - accuracy: 0.8365 - val_loss: 0.3744 - val_accuracy: 0.8370
Epoch 6/10
3410/3410 [==============================] - 8s 2ms/step - loss: 0.3831 - accuracy: 0.8373 - val_loss: 0.3734 - val_accuracy: 0.8373
Epoch 7/10
3410/3410 [==============================] - 8s 2ms/step - loss: 0.3820 - accuracy: 0.8377 - val_loss: 0.3724 - val_accuracy: 0.8387
Epoch 8/10
3410/3410 [==============================] - 8s 2ms/step - loss: 0.3807 - accuracy: 0.8382 - val_loss: 0.3725 - val_accuracy: 0.8391
Epoch 9/10
3410/3410 [==============================] - 8s 2ms/step - loss: 0.3798 - accuracy: 0.8382 - val_loss: 0.3713 - val_accuracy: 0.8391
Epoch 10/10
3410/3410 [==============================] - 8s 2ms/step - loss: 0.3798 - accuracy: 0.8375 - val_loss: 0.3711 - val_accuracy: 0.8389

import matplotlib.pyplot as plt

acc = model.history.history['accuracy']
val_acc = model.history.history['val_accuracy']

loss = model.history.history['loss']
val_loss = model.history.history['val_loss']

epochs_range = range(10)

plt.figure(figsize=(14, 4))
plt.subplot(1, 2, 1)

plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(1, 2, 2)
plt.plot(epochs_range, loss, label='Training Loss')
plt.plot(epochs_range, val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()