DL ICP5 - PardhaSaradhi74/Python GitHub Wiki
NAME
RAMINENI,PARDHA SARADHI
CLASS ID
32
In class programming:
1.Save the model and use the saved model to predict on new text data (ex, “A lot of good things are happening. We are respected again throughout the world, and that's a great thing.@realDonaldTrump”)
2.Apply GridSearchCV on the source code provided in the class
3.Apply the code on spamdata set availablein thesourcecode (text classification on the spam.csvdata set)
Bonus
Visualize Loss and Accuracy on the Tensorboard
SENTIMENTAL ANALYSIS ON TWITTER DATA
For this use case we saved the model and used the saved model to predict the sentiment value of the given tweet.
We applied few processing methods on the input tweet like tokenization and converting the text to sequence vectors.
Applying GridSearch CV
We applied the GridSearchCV on the model with params as batch size of 32,64 and the epochs as 1,2 and provided the model as estimator.
The best score is 0.679220 for the parameters batch_size: 64, epochs: 2
Use Case 2:SPAM DETECTION
We applied the same source code on the Spam Dataset by processing the feature and target columns of the Spam Dataset and evaluated the model. The accuracy of the model is 97.98%.