R3：基于lstm的天气预测
- 本文为365天深度学习训练营 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
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。你需要做的是根据这些数据对RainTomorrow进行一个预测
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("./data/weatherAUS.csv")
df = data.copy()
data.head()
data['Date'] = pd.to_datetime(data['Date'])
data['Date']
data['year'] = data['Date'].dt.year
data['Month'] = data['Date'].dt.month
data['day'] = data['Date'].dt.day
data.head()
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’)
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()
是否会下雨
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
y=x/x.transpose().sum().values.reshape(2,1)*100
y
● 如果今天不下雨，那么明天下雨的机会 = 15%
● 如果今天下雨明天下雨的机会 = 46%
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)
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
4. 湿度和压力对下雨的影响
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');
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。
5. 气温对下雨的影响
plt.figure(figsize=(8,6))
sns.scatterplot(x='MaxTemp', y='MinTemp', data=data, hue='RainTomorrow');
三、数据预处理
# 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
2. 构建数据集
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)
四、预测是否下雨
1. 搭建神经网络
from tensorflow.keras.optimizers import Adam
model = Sequential()
model.add(Dense(units=32,activation='tanh',))
model.add(Dense(units=24,activation='tanh'))
model.add(Dense(units=20,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)
2. 模型训练
model.fit(x=X_train,
y=y_train,
validation_data=(X_test, y_test), verbose=1,
callbacks=[early_stop],
epochs = 10,
batch_size = 32
)
3. 结果可视化
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()
