•  🍨 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

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("weatherAUS.csv")
df   = data.copy()
data.head()

#将数据转换为日期时间格式
data['Date'] = pd.to_datetime(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

二、探索式数据分析

2.1 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(numeric_only=True), 
                 square=True, 
                 annot=True, 
                 fmt='.2f')
ax.set_xticklabels(ax.get_xticklabels(), rotation=90)          
plt.show()

2.2 是否会下雨

# 设置样式和调色板
sns.set(style="whitegrid", palette="Set2")

# 创建一个 1 行 2 列的图像布局
fig, axes = plt.subplots(1, 2, figsize=(10, 4))  # 图形尺寸调大 (10, 4)

# 图表标题样式
title_font = {'fontsize': 14, 'fontweight': 'bold', 'color': 'darkblue'}

# 第一张图：RainTomorrow
sns.countplot(x='RainTomorrow', data=data, ax=axes[0], edgecolor='black')  # 添加边框
axes[0].set_title('Rain Tomorrow', fontdict=title_font)  # 设置标题
axes[0].set_xlabel('Will it Rain Tomorrow?', fontsize=12)  # X轴标签
axes[0].set_ylabel('Count', fontsize=12)  # Y轴标签
axes[0].tick_params(axis='x', labelsize=11)  # X轴刻度字体大小
axes[0].tick_params(axis='y', labelsize=11)  # Y轴刻度字体大小

# 第二张图：RainToday
sns.countplot(x='RainToday', data=data, ax=axes[1], edgecolor='black')  # 添加边框
axes[1].set_title('Rain Today', fontdict=title_font)  # 设置标题
axes[1].set_xlabel('Did it Rain Today?', fontsize=12)  # X轴标签
axes[1].set_ylabel('Count', fontsize=12)  # Y轴标签
axes[1].tick_params(axis='x', labelsize=11)  # X轴刻度字体大小
axes[1].tick_params(axis='y', labelsize=11)  # Y轴刻度字体大小

sns.despine()      # 去除图表顶部和右侧的边框
plt.tight_layout() # 调整布局，避免图形之间的重叠
plt.show()

x=pd.crosstab(data['RainTomorrow'],data['RainToday'])
x
y=x/x.transpose().sum().values.reshape(2,1)*100
y
y.plot(kind="bar",figsize=(4,3),color=['#006666','#d279a6']);

2.3 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)

2.4 温度和压力对下雨的影响

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');

2.5 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

3.1 处理缺失值

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

# 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

# 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

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

data.isnull().sum()

3.2 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、预测是否会下雨

4.1 搭建神经网络

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)

4.2 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
)

4.3 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()