标签：loss 20 train 阿里 import cnn 天池 250 accuracy
数据
访问链接查看大赛要求
https://tianchi.aliyun.com/competition/entrance/531810/introduction
数据描述：
模型（cnn）
代码
import pandas as pd
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score
#from sklearn.model_selection import GridSearchCV
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
from sklearn.metrics import confusion_matrix
from sklearn.metrics import roc_curve,auc
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Flatten
from keras.layers.embeddings import Embedding
from keras.preprocessing import sequence
import keras
import numpy as np
train_df = pd.read_csv('train_set.csv', sep='\t')
test_df = pd.read_csv('test_a.csv', sep='\t', nrows=None)
from sklearn.model_selection import train_test_split
X_train, X_val, y_train, y_val = train_test_split(
train_df['text'].iloc[:].values, train_df['label'].iloc[:].values,
test_size=0.05, random_state=42
)
len(list(pd.Series(y_train).value_counts().index))
14
print(len(X_train))
190000
def chuli_data(datas):
results = []
for rr in datas:
results.append(rr.split())
return results
X_train = chuli_data(X_train[:25000])
X_val = chuli_data(X_val[:3000])
y_train=y_train[:25000]
y_val = y_val[:3000]
X_test=test_df['text'].iloc[:].values
from keras.preprocessing.sequence import pad_sequences
X_test=chuli_data(X_test)
X_tests = pad_sequences(X_test, maxlen=500)
X_train = pad_sequences(X_train, maxlen=500)
X_val = pad_sequences(X_val, maxlen=500)
sequence_length=X_train.shape[1]
vocab_size = np.max([np.max(X_train[i]) for i in range(X_train.shape[0])]) + 1
#文本特征向量化
vocab_size
7550
y_train = keras.utils.to_categorical(y_train,num_classes=14)
y_val = keras.utils.to_categorical(y_val,num_classes=14)
from keras.models import Sequential
from keras.layers.embeddings import Embedding
from keras.preprocessing import sequence
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv1D, MaxPooling1D
from keras import optimizers
model = Sequential()
model.add(Embedding(vocab_size, 64, input_length = 500))#词汇表里词,词向量的维度64,输入序列的长度500
model.add(Conv1D(filters = 64, kernel_size = 3, padding = 'same', activation = 'relu'))
model.add(MaxPooling1D(pool_size = 2))
model.add(Conv1D(filters = 128, kernel_size = 3, padding = 'same',activation = 'relu'))
model.add(MaxPooling1D(pool_size = 2))
model.add(Conv1D(filters = 256, kernel_size = 3, padding = 'same',activation = 'relu'))
model.add(MaxPooling1D(pool_size = 2))
model.add(Flatten())
model.add(Dense(512, activation = 'relu'))
model.add(Dense(units=14,activation='softmax'))
model.compile(loss = 'categorical_crossentropy', optimizer=optimizers.RMSprop(lr=1e-4,rho=0.9, epsilon=1e-06), metrics = ['accuracy'])
print(model.summary())
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding (Embedding) (None, 500, 64) 483200
_________________________________________________________________
conv1d (Conv1D) (None, 500, 64) 12352
_________________________________________________________________
max_pooling1d (MaxPooling1D) (None, 250, 64) 0
_________________________________________________________________
conv1d_1 (Conv1D) (None, 250, 128) 24704
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None, 125, 128) 0
_________________________________________________________________
conv1d_2 (Conv1D) (None, 125, 256) 98560
_________________________________________________________________
max_pooling1d_2 (MaxPooling1 (None, 62, 256) 0
_________________________________________________________________
flatten (Flatten) (None, 15872) 0
_________________________________________________________________
dense (Dense) (None, 512) 8126976
_________________________________________________________________
dense_1 (Dense) (None, 14) 7182
=================================================================
Total params: 8,752,974
Trainable params: 8,752,974
Non-trainable params: 0
_________________________________________________________________
None
model.fit(X_train, y_train,epochs = 20, batch_size = 100)
Epoch 1/20
250/250 [==============================] - 86s 319ms/step - loss: 2.1802 - accuracy: 0.2573
Epoch 2/20
250/250 [==============================] - 83s 330ms/step - loss: 1.3863 - accuracy: 0.5673
Epoch 3/20
250/250 [==============================] - 77s 309ms/step - loss: 1.0288 - accuracy: 0.6795
Epoch 4/20
250/250 [==============================] - 79s 317ms/step - loss: 0.8081 - accuracy: 0.7536
Epoch 5/20
250/250 [==============================] - 79s 316ms/step - loss: 0.6772 - accuracy: 0.7920
Epoch 6/20
250/250 [==============================] - 79s 316ms/step - loss: 0.5864 - accuracy: 0.8211
Epoch 7/20
250/250 [==============================] - 78s 310ms/step - loss: 0.5259 - accuracy: 0.8453
Epoch 8/20
250/250 [==============================] - 80s 319ms/step - loss: 0.4837 - accuracy: 0.8605
Epoch 9/20
250/250 [==============================] - 78s 312ms/step - loss: 0.4258 - accuracy: 0.8741
Epoch 10/20
250/250 [==============================] - 101s 404ms/step - loss: 0.3973 - accuracy: 0.8835
Epoch 11/20
250/250 [==============================] - 90s 359ms/step - loss: 0.3526 - accuracy: 0.8953
Epoch 12/20
250/250 [==============================] - 82s 330ms/step - loss: 0.3320 - accuracy: 0.9021
Epoch 13/20
250/250 [==============================] - 80s 319ms/step - loss: 0.2963 - accuracy: 0.9123
Epoch 14/20
250/250 [==============================] - 83s 332ms/step - loss: 0.2703 - accuracy: 0.9213
Epoch 15/20
250/250 [==============================] - 94s 375ms/step - loss: 0.2452 - accuracy: 0.9263
Epoch 16/20
250/250 [==============================] - 90s 360ms/step - loss: 0.2297 - accuracy: 0.9322
Epoch 17/20
250/250 [==============================] - 90s 359ms/step - loss: 0.2058 - accuracy: 0.9390
Epoch 18/20
250/250 [==============================] - 91s 364ms/step - loss: 0.1913 - accuracy: 0.9422
Epoch 19/20
250/250 [==============================] - 93s 371ms/step - loss: 0.1741 - accuracy: 0.9479
Epoch 20/20
250/250 [==============================] - 92s 369ms/step - loss: 0.1504 - accuracy: 0.9590
<tensorflow.python.keras.callbacks.History at 0x176dcc9cb80>
model.evaluate(X_val,y_val,batch_size=100)
30/30 [==============================] - 3s 75ms/step - loss: 0.4943 - accuracy: 0.8620
[0.49429306387901306, 0.8619999885559082]
results = model.predict(X_tests)
标签：loss,20,train,阿里,import,cnn,天池,250,accuracy 来源： https://blog.csdn.net/qq_43997786/article/details/116952242
本站声明： 1. iCode9 技术分享网（下文简称本站）提供的所有内容，仅供技术学习、探讨和分享； 2. 关于本站的所有留言、评论、转载及引用，纯属内容发起人的个人观点，与本站观点和立场无关； 3. 关于本站的所有言论和文字，纯属内容发起人的个人观点，与本站观点和立场无关； 4. 本站文章均是网友提供，不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属；如您发现该文章侵犯了您的权益，可联系我们第一时间进行删除； 5. 本站为非盈利性的个人网站，所有内容不会用来进行牟利，也不会利用任何形式的广告来间接获益，纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。