Class IMDB

Dataset of 25,000 movies reviews from IMDB, labeled by sentiment (positive/negative). Reviews have been preprocessed, and each review is encoded as a sequence of word indexes (integers). For convenience, words are indexed by overall frequency in the dataset, so that for instance the integer "3" encodes the 3rd most frequent word in the data. This allows for quick filtering operations such as: "only consider the top 10,000 most common words, but eliminate the top 20 most common words". As a convention, "0" does not stand for a specific word, but instead is used to encode any unknown word.

Inheritance
System.Object
Keras
Base
IMDB
Implements
System.IDisposable
Inherited Members
System.Object.Equals(System.Object)
System.Object.Equals(System.Object, System.Object)
System.Object.GetHashCode()
System.Object.GetType()
System.Object.MemberwiseClone()
System.Object.ReferenceEquals(System.Object, System.Object)
System.Object.ToString()
Namespace: Keras.Datasets
Assembly: Keras.dll
Syntax
public class IMDB : Base, IDisposable

Methods

| Improve this Doc View Source

GetWordIndex(String)

Gets the index of the word.

Declaration
public static Dictionary<string, int> GetWordIndex(string path = "imdb_word_index.json")
Parameters
Type Name Description
System.String path

The path.
Returns
Type Description
System.Collections.Generic.Dictionary<System.String, System.Int32>
| Improve this Doc View Source

LoadData(String, Nullable<Int32>, Int32, Nullable<Int32>, Int32, Int32, Int32, Int32)

Loads the data.

Declaration
public static ((NDarray, NDarray), (NDarray, NDarray))LoadData(string path = "imdb.npz", int? num_words = default(int? ), int skip_top = 0, int? maxlen = default(int? ), int seed = 113, int start_char = 1, int oov_char = 2, int index_from = 3)
Parameters
Type Name Description
System.String path

if you do not have the data locally (at '~/.keras/datasets/' + path), it will be downloaded to this location.
System.Nullable<System.Int32> num_words

integer or None. Top most frequent words to consider. Any less frequent word will appear as oov_char value in the sequence data.
System.Int32 skip_top

integer. Top most frequent words to ignore (they will appear as oov_char value in the sequence data).
System.Nullable<System.Int32> maxlen

int. Maximum sequence length. Any longer sequence will be truncated.
System.Int32 seed

int. Seed for reproducible data shuffling.
System.Int32 start_char

int. The start of a sequence will be marked with this character. Set to 1 because 0 is usually the padding character.
System.Int32 oov_char

int. words that were cut out because of the num_words or skip_top limit will be replaced with this character.
System.Int32 index_from

int. Index actual words with this index and higher.
Returns
Type Description
System.ValueTuple<System.ValueTuple<Numpy.NDarray, Numpy.NDarray>, System.ValueTuple<Numpy.NDarray, Numpy.NDarray>>

Implements

System.IDisposable