- 本文为365天深度学习训练营 中的学习记录博客
- 原作者：K同学啊
任务说明：该数据集提供了来自澳大利亚许多地点的大约 10 年的每日天气观测数据。需要做的是根据这些数据对RainTomorrow进行一个预测，这次任务任务与以往的不同，增加了探索式数据分析（EDA），希望这部分内容可以帮助到大家。
我的环境：
●语言环境：Python3.8
●编译器：Jupyter Lab
●深度学习框架：torch 1.10.2 (cpu)
●数据：天气数据集
一、导入数据
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("./R3/weatherAUS.csv")
df = data.copy()
data.head()
代码输出：
| 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()
代码输出：
| 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
代码输出：
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']
代码输出：
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
data.head()
代码输出：
| 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
代码输出：
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')
二、探索式数据分析（EDA）
- 数据相关性探索
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()
代码输出：
- 是否会下雨
sns.set(style="darkgrid")
plt.figure(figsize=(4,3))
sns.countplot(x='RainTomorrow',data=data)
代码输出：
<matplotlib.axes._subplots.AxesSubplot at 0x1afec66fcc0>
plt.figure(figsize=(4,3))
sns.countplot(x='RainToday',data=data)
代码输出：
<matplotlib.axes._subplots.AxesSubplot at 0x1afed091208>
x=pd.crosstab(data['RainTomorrow'],data['RainToday'])
x
代码输出：
| RainToday | No | Yes |
|---|---|---|
| RainTomorrow | ||
| No | 92728 | 16858 |
| Yes | 16604 | 14597 |
y=x/x.transpose().sum().values.reshape(2,1)*100
y
代码输出：
| RainToday | No | Yes |
|---|---|---|
| RainTomorrow | ||
| No | 84.616648 | 15.383352 |
| Yes | 53.216243 | 46.783757 |
●如果今天不下雨，那么明天下雨的机会 = 53.22%
●如果今天下雨明天下雨的机会 = 46.78%
y.plot(kind="bar",figsize=(4,3),color=['#006666','#d279a6']);
- 地理位置与下雨的关系
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)
代码输出：
<matplotlib.axes._subplots.AxesSubplot at 0x1afe642bf28>
位置影响下雨，对于 Portland 来说，有 36% 的时间在下雨，而对于 Woomers 来说，只有6%的时间在下雨
- 湿度和压力对下雨的影响
data.columns
代码输出：
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');
代码输出：
低压与高湿度会增加第二天下雨的概率，尤其是下午 3 点的空气湿度。
- 气温对下雨的影响
plt.figure(figsize=(8,6))
sns.scatterplot(x='MaxTemp', y='MinTemp', data=data, hue='RainTomorrow');
代码输出：
结论：当一天的最高气温和最低气温接近时，第二天下雨的概率会增加。
三、数据预处理
- 处理缺损值
# 每列中缺失数据的百分比
data.isnull().sum()/data.shape[0]*100
代码输出：
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
代码输出：
['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
代码输出：
['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()
代码输出：
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
- 构建数据集
from sklearn.preprocessing import LabelEncoderlabel_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)
四、预测是否下雨
- 搭建神经网络
from tensorflow.keras.optimizers import Adammodel = 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)
- 模型训练
model.fit(x=X_train, y=y_train, validation_data=(X_test, y_test), verbose=1,callbacks=[early_stop],epochs = 100,batch_size = 32
)
代码输出：
Epoch 1/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.5179 - accuracy: 0.7616 - val_loss: 0.3891 - val_accuracy: 0.8306
Epoch 2/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.4012 - accuracy: 0.8307 - val_loss: 0.3778 - val_accuracy: 0.8360
Epoch 3/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3923 - accuracy: 0.8343 - val_loss: 0.3749 - val_accuracy: 0.8371
Epoch 4/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3856 - accuracy: 0.8366 - val_loss: 0.3735 - val_accuracy: 0.8384
Epoch 5/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3855 - accuracy: 0.8371 - val_loss: 0.3721 - val_accuracy: 0.8388
Epoch 6/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3835 - accuracy: 0.8366 - val_loss: 0.3714 - val_accuracy: 0.8393
Epoch 7/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3808 - accuracy: 0.8387 - val_loss: 0.3706 - val_accuracy: 0.8389
Epoch 8/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3790 - accuracy: 0.8373 - val_loss: 0.3698 - val_accuracy: 0.8400
Epoch 9/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3818 - accuracy: 0.8368 - val_loss: 0.3695 - val_accuracy: 0.8397
Epoch 10/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3784 - accuracy: 0.8383 - val_loss: 0.3691 - val_accuracy: 0.8398
Epoch 11/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3775 - accuracy: 0.8394 - val_loss: 0.3688 - val_accuracy: 0.8402
Epoch 12/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3798 - accuracy: 0.8370 - val_loss: 0.3687 - val_accuracy: 0.8399
Epoch 13/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3767 - accuracy: 0.8389 - val_loss: 0.3684 - val_accuracy: 0.8401
Epoch 14/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3751 - accuracy: 0.8397 - val_loss: 0.3690 - val_accuracy: 0.8398
Epoch 15/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3736 - accuracy: 0.8415 - val_loss: 0.3682 - val_accuracy: 0.8404
Epoch 16/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3743 - accuracy: 0.8410 - val_loss: 0.3678 - val_accuracy: 0.8409
Epoch 17/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3752 - accuracy: 0.8406 - val_loss: 0.3680 - val_accuracy: 0.8409
Epoch 18/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3777 - accuracy: 0.8382 - val_loss: 0.3675 - val_accuracy: 0.8404
Epoch 19/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3735 - accuracy: 0.8394 - val_loss: 0.3673 - val_accuracy: 0.8409
Epoch 20/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3751 - accuracy: 0.8389 - val_loss: 0.3673 - val_accuracy: 0.8407
Epoch 21/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3715 - accuracy: 0.8394 - val_loss: 0.3670 - val_accuracy: 0.8408
Epoch 22/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3758 - accuracy: 0.8391 - val_loss: 0.3667 - val_accuracy: 0.8406
Epoch 23/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3715 - accuracy: 0.8411 - val_loss: 0.3668 - val_accuracy: 0.8406
Epoch 24/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3744 - accuracy: 0.8405 - val_loss: 0.3686 - val_accuracy: 0.8401
Epoch 25/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3754 - accuracy: 0.8393 - val_loss: 0.3666 - val_accuracy: 0.8414
Epoch 26/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3720 - accuracy: 0.8415 - val_loss: 0.3658 - val_accuracy: 0.8412
Epoch 27/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3694 - accuracy: 0.8413 - val_loss: 0.3656 - val_accuracy: 0.8417
Epoch 28/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3733 - accuracy: 0.8411 - val_loss: 0.3676 - val_accuracy: 0.8390
Epoch 29/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3715 - accuracy: 0.8413 - val_loss: 0.3655 - val_accuracy: 0.8417
Epoch 30/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3707 - accuracy: 0.8417 - val_loss: 0.3655 - val_accuracy: 0.8420
Epoch 31/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3754 - accuracy: 0.8393 - val_loss: 0.3653 - val_accuracy: 0.8419
Epoch 32/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3694 - accuracy: 0.8423 - val_loss: 0.3651 - val_accuracy: 0.8416
Epoch 33/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3717 - accuracy: 0.8422 - val_loss: 0.3657 - val_accuracy: 0.8411
Epoch 34/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3743 - accuracy: 0.8399 - val_loss: 0.3648 - val_accuracy: 0.8417
Epoch 35/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3690 - accuracy: 0.8426 - val_loss: 0.3647 - val_accuracy: 0.8416
Epoch 36/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3723 - accuracy: 0.8408 - val_loss: 0.3645 - val_accuracy: 0.8423
Epoch 37/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3715 - accuracy: 0.8414 - val_loss: 0.3649 - val_accuracy: 0.8402
Epoch 38/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3680 - accuracy: 0.8429 - val_loss: 0.3644 - val_accuracy: 0.8421
Epoch 39/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3711 - accuracy: 0.8416 - val_loss: 0.3664 - val_accuracy: 0.8411
Epoch 40/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3726 - accuracy: 0.8395 - val_loss: 0.3641 - val_accuracy: 0.8415
Epoch 41/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3695 - accuracy: 0.8425 - val_loss: 0.3643 - val_accuracy: 0.8411
Epoch 42/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3698 - accuracy: 0.8429 - val_loss: 0.3637 - val_accuracy: 0.8416
Epoch 43/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3666 - accuracy: 0.8425 - val_loss: 0.3632 - val_accuracy: 0.8414
Epoch 44/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3659 - accuracy: 0.8426 - val_loss: 0.3637 - val_accuracy: 0.8416
Epoch 45/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3696 - accuracy: 0.8434 - val_loss: 0.3635 - val_accuracy: 0.8411
Epoch 46/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3660 - accuracy: 0.8436 - val_loss: 0.3628 - val_accuracy: 0.8419
Epoch 47/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3728 - accuracy: 0.8401 - val_loss: 0.3659 - val_accuracy: 0.8418
Epoch 48/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3696 - accuracy: 0.8408 - val_loss: 0.3628 - val_accuracy: 0.8420
Epoch 49/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3674 - accuracy: 0.8426 - val_loss: 0.3629 - val_accuracy: 0.8409
Epoch 50/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3654 - accuracy: 0.8439 - val_loss: 0.3663 - val_accuracy: 0.8414
Epoch 51/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3695 - accuracy: 0.8421 - val_loss: 0.3624 - val_accuracy: 0.8422
Epoch 52/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3671 - accuracy: 0.8424 - val_loss: 0.3621 - val_accuracy: 0.8422
Epoch 53/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3710 - accuracy: 0.8410 - val_loss: 0.3621 - val_accuracy: 0.8419
Epoch 54/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3686 - accuracy: 0.8418 - val_loss: 0.3621 - val_accuracy: 0.8421
Epoch 55/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3673 - accuracy: 0.8429 - val_loss: 0.3622 - val_accuracy: 0.8419
Epoch 56/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3670 - accuracy: 0.8416 - val_loss: 0.3627 - val_accuracy: 0.8406
Epoch 57/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3665 - accuracy: 0.8413 - val_loss: 0.3620 - val_accuracy: 0.8412
Epoch 58/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3680 - accuracy: 0.8428 - val_loss: 0.3616 - val_accuracy: 0.8420
Epoch 59/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3679 - accuracy: 0.8413 - val_loss: 0.3626 - val_accuracy: 0.8400
Epoch 60/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3660 - accuracy: 0.8427 - val_loss: 0.3613 - val_accuracy: 0.8428
Epoch 61/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3659 - accuracy: 0.8431 - val_loss: 0.3612 - val_accuracy: 0.8421
Epoch 62/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3681 - accuracy: 0.8411 - val_loss: 0.3610 - val_accuracy: 0.8417
Epoch 63/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3661 - accuracy: 0.8434 - val_loss: 0.3609 - val_accuracy: 0.8424
Epoch 64/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3606 - accuracy: 0.8462 - val_loss: 0.3615 - val_accuracy: 0.8432
Epoch 65/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3657 - accuracy: 0.8449 - val_loss: 0.3614 - val_accuracy: 0.8419
Epoch 66/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3646 - accuracy: 0.8447 - val_loss: 0.3613 - val_accuracy: 0.8431
Epoch 67/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3653 - accuracy: 0.8433 - val_loss: 0.3615 - val_accuracy: 0.8412
Epoch 68/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3651 - accuracy: 0.8428 - val_loss: 0.3609 - val_accuracy: 0.8428
Epoch 69/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3649 - accuracy: 0.8445 - val_loss: 0.3604 - val_accuracy: 0.8422
Epoch 70/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3669 - accuracy: 0.8426 - val_loss: 0.3608 - val_accuracy: 0.8426
Epoch 71/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3644 - accuracy: 0.8447 - val_loss: 0.3615 - val_accuracy: 0.8431
Epoch 72/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3611 - accuracy: 0.8470 - val_loss: 0.3611 - val_accuracy: 0.8411
Epoch 73/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3630 - accuracy: 0.8445 - val_loss: 0.3617 - val_accuracy: 0.8408
Epoch 74/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3681 - accuracy: 0.8415 - val_loss: 0.3598 - val_accuracy: 0.8432
Epoch 75/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3638 - accuracy: 0.8443 - val_loss: 0.3596 - val_accuracy: 0.8432
Epoch 76/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3639 - accuracy: 0.8432 - val_loss: 0.3602 - val_accuracy: 0.8427
Epoch 77/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3635 - accuracy: 0.8446 - val_loss: 0.3597 - val_accuracy: 0.8423
Epoch 78/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3637 - accuracy: 0.8446 - val_loss: 0.3613 - val_accuracy: 0.8430
Epoch 79/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3659 - accuracy: 0.8427 - val_loss: 0.3647 - val_accuracy: 0.8428
Epoch 80/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3662 - accuracy: 0.8432 - val_loss: 0.3605 - val_accuracy: 0.8414
Epoch 81/100
3410/3410 [==============================] - 6s 2ms/step - loss: 0.3662 - accuracy: 0.8429 - val_loss: 0.3592 - val_accuracy: 0.8431
Epoch 82/100
3410/3410 [==============================] - 6s 2ms/step - loss: 0.3661 - accuracy: 0.8435 - val_loss: 0.3595 - val_accuracy: 0.8425
Epoch 83/100
3410/3410 [==============================] - 6s 2ms/step - loss: 0.3634 - accuracy: 0.8445 - val_loss: 0.3592 - val_accuracy: 0.8434
Epoch 84/100
3410/3410 [==============================] - 6s 2ms/step - loss: 0.3642 - accuracy: 0.8441 - val_loss: 0.3591 - val_accuracy: 0.8428
Epoch 85/100
3410/3410 [==============================] - 6s 2ms/step - loss: 0.3608 - accuracy: 0.8457 - val_loss: 0.3595 - val_accuracy: 0.8429
Epoch 86/100
3410/3410 [==============================] - 6s 2ms/step - loss: 0.3620 - accuracy: 0.8464 - val_loss: 0.3591 - val_accuracy: 0.8436
Epoch 87/100
3410/3410 [==============================] - 6s 2ms/step - loss: 0.3653 - accuracy: 0.8430 - val_loss: 0.3604 - val_accuracy: 0.8432
Epoch 88/100
3410/3410 [==============================] - 6s 2ms/step - loss: 0.3654 - accuracy: 0.8427 - val_loss: 0.3686 - val_accuracy: 0.8367
Epoch 89/100
3410/3410 [==============================] - 7s 2ms/step - loss: 0.3594 - accuracy: 0.8468 - val_loss: 0.3589 - val_accuracy: 0.8428
Epoch 90/100
3410/3410 [==============================] - 6s 2ms/step - loss: 0.3636 - accuracy: 0.8446 - val_loss: 0.3588 - val_accuracy: 0.8436
Epoch 91/100
3410/3410 [==============================] - 6s 2ms/step - loss: 0.3657 - accuracy: 0.8444 - val_loss: 0.3607 - val_accuracy: 0.8432
Epoch 92/100
3410/3410 [==============================] - 6s 2ms/step - loss: 0.3628 - accuracy: 0.8441 - val_loss: 0.3588 - val_accuracy: 0.8437
Epoch 93/100
3410/3410 [==============================] - 6s 2ms/step - loss: 0.3666 - accuracy: 0.8427 - val_loss: 0.3596 - val_accuracy: 0.8423
Epoch 94/100
3410/3410 [==============================] - 6s 2ms/step - loss: 0.3659 - accuracy: 0.8421 - val_loss: 0.3594 - val_accuracy: 0.8441
Epoch 95/100
3410/3410 [==============================] - 6s 2ms/step - loss: 0.3623 - accuracy: 0.8459 - val_loss: 0.3583 - val_accuracy: 0.8438
Epoch 96/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3604 - accuracy: 0.8459 - val_loss: 0.3586 - val_accuracy: 0.8439
Epoch 97/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3633 - accuracy: 0.8436 - val_loss: 0.3588 - val_accuracy: 0.8415
Epoch 98/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3618 - accuracy: 0.8471 - val_loss: 0.3582 - val_accuracy: 0.8440
Epoch 99/100
3410/3410 [==============================] - 4s 1ms/step - loss: 0.3633 - accuracy: 0.8452 - val_loss: 0.3627 - val_accuracy: 0.8433
Epoch 100/100
3410/3410 [==============================] - 5s 1ms/step - loss: 0.3600 - accuracy: 0.8458 - val_loss: 0.3584 - val_accuracy: 0.8441<tensorflow.python.keras.callbacks.History at 0x1afed021128>
- 结果可视化
import matplotlib.pyplot as pltacc = 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(100)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()
代码输出：
