├── requirements.txt
├── README.md
└── Poetry NLP Notebook.ipynb


/requirements.txt:
--------------------------------------------------------------------------------
 1 | absl-py==0.9.0
 2 | astunparse==1.6.3
 3 | cachetools==4.1.0
 4 | certifi==2020.4.5.1
 5 | chardet==3.0.4
 6 | click==7.1.2
 7 | cycler==0.10.0
 8 | gast==0.3.3
 9 | google-auth==1.15.0
10 | google-auth-oauthlib==0.4.1
11 | google-pasta==0.2.0
12 | grpcio==1.29.0
13 | h5py==2.10.0
14 | idna==2.9
15 | importlib-metadata==1.6.0
16 | joblib==0.15.1
17 | Keras-Preprocessing==1.1.2
18 | kiwisolver==1.2.0
19 | Markdown==3.2.2
20 | matplotlib==3.2.1
21 | nltk==3.5
22 | numpy==1.18.4
23 | oauthlib==3.1.0
24 | opt-einsum==3.2.1
25 | pandas==1.0.3
26 | Pillow==7.1.2
27 | protobuf==3.12.2
28 | pyasn1==0.4.8
29 | pyasn1-modules==0.2.8
30 | pyparsing==2.4.7
31 | python-dateutil==2.8.1
32 | pytz==2020.1
33 | regex==2020.5.14
34 | requests==2.23.0
35 | requests-oauthlib==1.3.0
36 | rsa==4.0
37 | scikit-learn==0.23.1
38 | scipy==1.4.1
39 | seaborn==0.10.1
40 | six==1.15.0
41 | sklearn==0.0
42 | tensorboard==2.2.1
43 | tensorboard-plugin-wit==1.6.0.post3
44 | tensorflow==2.2.0
45 | tensorflow-estimator==2.2.0
46 | termcolor==1.1.0
47 | threadpoolctl==2.0.0
48 | tqdm==4.46.0
49 | urllib3==1.25.9
50 | Werkzeug==1.0.1
51 | wordcloud==1.7.0
52 | wrapt==1.12.1
53 | zipp==3.1.0


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | 
 2 | 
 3 | # Poetry Classification Notebook
 4 | ![Poetry Classification Header](https://images-wixmp-ed30a86b8c4ca887773594c2.wixmp.com/f/05df8cc2-4413-4a7c-93c7-dbf7991b18a7/ddxz5h4-a844ba43-c2fe-4cf5-a54b-7b0b106a0edc.png?token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJzdWIiOiJ1cm46YXBwOiIsImlzcyI6InVybjphcHA6Iiwib2JqIjpbW3sicGF0aCI6IlwvZlwvMDVkZjhjYzItNDQxMy00YTdjLTkzYzctZGJmNzk5MWIxOGE3XC9kZHh6NWg0LWE4NDRiYTQzLWMyZmUtNGNmNS1hNTRiLTdiMGIxMDZhMGVkYy5wbmcifV1dLCJhdWQiOlsidXJuOnNlcnZpY2U6ZmlsZS5kb3dubG9hZCJdfQ.-VnjZYfWlvW4BkECBqug2QCGpK7hwvPccE8GESLzxtU)
 5 | This notebook includes classification of poetry ages and authors with both RNNs and decision trees (because the size of data is too small).
 6 | 
 7 | 
 8 | ## Models and Data Used
 9 | 
10 | -   Data: Poetry from various poets such as William Shakespeare, different genres and different ages.
11 | -   Classification Methods: Decision Trees (sklearn) and RNNs (tf.keras)
12 | 
13 | ![Decision Trees vs NN](https://images-wixmp-ed30a86b8c4ca887773594c2.wixmp.com/f/05df8cc2-4413-4a7c-93c7-dbf7991b18a7/ddxyf2e-20784a4b-c60d-45c6-8fe1-4a281665d670.png/v1/fill/w_1280,h_487,q_80,strp/vs_by_markdownimgmn_ddxyf2e-fullview.jpg?token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJzdWIiOiJ1cm46YXBwOiIsImlzcyI6InVybjphcHA6Iiwib2JqIjpbW3siaGVpZ2h0IjoiPD00ODciLCJwYXRoIjoiXC9mXC8wNWRmOGNjMi00NDEzLTRhN2MtOTNjNy1kYmY3OTkxYjE4YTdcL2RkeHlmMmUtMjA3ODRhNGItYzYwZC00NWM2LThmZTEtNGEyODE2NjVkNjcwLnBuZyIsIndpZHRoIjoiPD0xMjgwIn1dXSwiYXVkIjpbInVybjpzZXJ2aWNlOmltYWdlLm9wZXJhdGlvbnMiXX0.3K_JTqac7uTpP6dZCKybJxUrQitNVPk3x9p-Zqeyz_Y)
14 | 
15 | # Files
16 | 
17 | - *all.csv* including data taken from [kaggle](https://www.kaggle.com/ishnoor/poetry-analysis-with-machine-learning?select=all.csv)
18 | - *poetry-nlp-notebook.ipynb* Interactive Python Notebook that includes the code itself
19 | 
20 | ## Libraries Used
21 | 
22 |     nltk
23 |     re
24 |     keras
25 |     seaborn
26 |     matplotlib
27 |     scikit-learn
28 |     pandas
29 |     tensorflow
30 |     numpy
31 |     wordcloud
32 |     ps: All the libraries can be downloaded by pip install -r requirements.txt
33 | 
34 | 
35 | ## Author
36 | 
37 | -   **Merve Noyan**  - [merveenoyan](https://github.com/merveenoyan)
38 | 
39 | ## Further Notes
40 | Will migrate this project to tensorflow and generate poetry, stay tuned and watch this repo if you don't want to miss 🤓
41 | 
42 | > Written with [StackEdit](https://stackedit.io/).
43 | 
44 | 


--------------------------------------------------------------------------------
/Poetry NLP Notebook.ipynb:
--------------------------------------------------------------------------------
1 | {"cells":[{"metadata":{},"cell_type":"markdown","source":"**Poetry Classification Notebook**"},{"metadata":{},"cell_type":"markdown","source":"I've came across this dataset as I was looking for renaissance paintings to use in GAN, and seeing there are no kernels on it, I thought I might just dive in. \nThere are five columns, the poetry itself, the type, author, age of it. First I'll do exploratory data analysis and preprocessing, then I'll classify the author and the age of the poetries using decision trees."},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nfrom sklearn.model_selection import train_test_split\nfrom sklearn import preprocessing\nfrom sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer\nfrom sklearn.metrics import classification_report, confusion_matrix\nfrom sklearn.metrics import accuracy_score\nfrom nltk.corpus import stopwords\nfrom nltk.corpus import stopwords\nfrom wordcloud import WordCloud, STOPWORDS\nfrom sklearn.tree import DecisionTreeClassifier\nimport seaborn as sns\nimport gc\nimport re","execution_count":2,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.layers import GRU, LSTM, Embedding\nfrom tensorflow.keras.callbacks import EarlyStopping\nfrom tensorflow.keras import optimizers\nfrom tensorflow.keras.layers import Activation, Dense, Bidirectional","execution_count":3,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Importing the dataset**"},{"metadata":{"trusted":true},"cell_type":"code","source":"df_poetry=pd.read_csv(\"../input/poetry-analysis-with-machine-learning/all.csv\", sep=\",\")\ndf_poetry.head()","execution_count":4,"outputs":[{"output_type":"execute_result","execution_count":4,"data":{"text/plain":"                                    author  \\\n0                      WILLIAM SHAKESPEARE   \n1  DUCHESS OF NEWCASTLE MARGARET CAVENDISH   \n2                           THOMAS BASTARD   \n3                           EDMUND SPENSER   \n4                        RICHARD BARNFIELD   \n\n                                             content  \\\n0  Let the bird of loudest lay\\r\\nOn the sole Ara...   \n1  Sir Charles into my chamber coming in,\\r\\nWhen...   \n2  Our vice runs beyond all that old men saw,\\r\\n...   \n3  Lo I the man, whose Muse whilome did maske,\\r\\...   \n4  Long have I longd to see my love againe,\\r\\nSt...   \n\n                                 poem name          age                  type  \n0               The Phoenix and the Turtle  Renaissance  Mythology & Folklore  \n1                 An Epilogue to the Above  Renaissance  Mythology & Folklore  \n2                       Book 7, Epigram 42  Renaissance  Mythology & Folklore  \n3  from The Faerie Queene: Book I, Canto I  Renaissance  Mythology & Folklore  \n4                                Sonnet 16  Renaissance  Mythology & Folklore  ","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>author</th>\n      <th>content</th>\n      <th>poem name</th>\n      <th>age</th>\n      <th>type</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>WILLIAM SHAKESPEARE</td>\n      <td>Let the bird of loudest lay\\r\\nOn the sole Ara...</td>\n      <td>The Phoenix and the Turtle</td>\n      <td>Renaissance</td>\n      <td>Mythology &amp; Folklore</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>DUCHESS OF NEWCASTLE MARGARET CAVENDISH</td>\n      <td>Sir Charles into my chamber coming in,\\r\\nWhen...</td>\n      <td>An Epilogue to the Above</td>\n      <td>Renaissance</td>\n      <td>Mythology &amp; Folklore</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>THOMAS BASTARD</td>\n      <td>Our vice runs beyond all that old men saw,\\r\\n...</td>\n      <td>Book 7, Epigram 42</td>\n      <td>Renaissance</td>\n      <td>Mythology &amp; Folklore</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>EDMUND SPENSER</td>\n      <td>Lo I the man, whose Muse whilome did maske,\\r\\...</td>\n      <td>from The Faerie Queene: Book I, Canto I</td>\n      <td>Renaissance</td>\n      <td>Mythology &amp; Folklore</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>RICHARD BARNFIELD</td>\n      <td>Long have I longd to see my love againe,\\r\\nSt...</td>\n      <td>Sonnet 16</td>\n      <td>Renaissance</td>\n      <td>Mythology &amp; Folklore</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"First I'll do exploratory data analysis, then classify the poetries in age, type and author. Let's see the list of authors, types and ages."},{"metadata":{"trusted":true},"cell_type":"code","source":"df_poetry.rename(columns={\"poem name\":\"poem_name\"}, inplace=True)","execution_count":5,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_poetry.age.unique()","execution_count":6,"outputs":[{"output_type":"execute_result","execution_count":6,"data":{"text/plain":"array(['Renaissance', 'Modern'], dtype=object)"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"There are three types of poetry."},{"metadata":{"trusted":true},"cell_type":"code","source":"df_poetry.type.unique()","execution_count":7,"outputs":[{"output_type":"execute_result","execution_count":7,"data":{"text/plain":"array(['Mythology & Folklore', 'Nature', 'Love'], dtype=object)"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"Let's see the list of authors."},{"metadata":{"trusted":true},"cell_type":"code","source":"df_poetry.author.unique()","execution_count":8,"outputs":[{"output_type":"execute_result","execution_count":8,"data":{"text/plain":"array(['WILLIAM SHAKESPEARE', 'DUCHESS OF NEWCASTLE MARGARET CAVENDISH',\n       'THOMAS BASTARD', 'EDMUND SPENSER', 'RICHARD BARNFIELD',\n       'SIR WALTER RALEGH', 'QUEEN ELIZABETH I', 'JOHN DONNE',\n       'JOHN SKELTON', 'CHRISTOPHER MARLOWE', 'LADY MARY WROTH',\n       'ROBERT SOUTHWELL, SJ', 'WILLIAM BYRD', 'GEORGE GASCOIGNE',\n       'HENRY VIII, KING OF ENGLAND', 'SIR THOMAS WYATT', 'EN JONSON',\n       'ORLANDO GIBBONS', 'THOMAS NASHE', 'SIR PHILIP SIDNEY',\n       'SECOND BARON VAUX OF HARROWDEN THOMAS, LORD VAUX',\n       'HENRY HOWARD, EARL OF SURREY', 'GEORGE CHAPMAN', 'THOMAS CAMPION',\n       'ISABELLA WHITNEY', 'SAMUEL DANIEL', 'THOMAS HEYWOOD',\n       'GIOVANNI BATTISTA GUARINI', 'SIR EDWARD DYER', 'THOMAS LODGE',\n       'JOHN FLETCHER', 'EDGAR LEE MASTERS', 'WILLIAM BUTLER YEATS',\n       'FORD MADOX FORD', 'IVOR GURNEY', 'CARL SANDBURG', 'EZRA POUND',\n       'ELINOR WYLIE', 'GEORGE SANTAYANA', 'LOUISE BOGAN',\n       'KENNETH SLESSOR', 'HART CRANE', 'D. H. LAWRENCE',\n       'HUGH MACDIARMID', 'E. E. CUMMINGS', 'LOUIS UNTERMEYER',\n       'WALLACE STEVENS', 'MARJORIE PICKTHALL', 'RICHARD ALDINGTON',\n       'GUILLAUME APOLLINAIRE', 'SAMUEL GREENBERG', 'STEPHEN SPENDER',\n       'EDITH SITWELL', 'PAUL LAURENCE DUNBAR', 'SARA TEASDALE',\n       'MINA LOY', 'MARIANNE MOORE', 'ASIL BUNTING', 'MICHAEL ANANIA',\n       'ARCHIBALD MACLEISH', 'CONRAD AIKEN', 'MALCOLM COWLEY',\n       'KATHERINE MANSFIELD', 'T. S. ELIOT', 'GERTRUDE STEIN',\n       'JAMES JOYCE', 'KENNETH FEARING'], dtype=object)"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"**Removing special characters from the content column, leaving the spaces for tokenization**"},{"metadata":{"trusted":true},"cell_type":"code","source":"def remove_special_chars(text, remove_digits=True):\n    text=re.sub('[^a-zA-Z.\\d\\s]', '',text)\n    return text\ndf_poetry.content=df_poetry.content.apply(remove_special_chars)","execution_count":9,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Importing the list of stopwords, I have gathered the below gist def remove_stopwords from another notebook."},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.preprocessing import LabelEncoder\nle=LabelEncoder()\ndf_poetry.age=le.fit_transform(df_poetry.age)\ndf_poetry","execution_count":10,"outputs":[{"output_type":"execute_result","execution_count":10,"data":{"text/plain":"                                      author  \\\n0                        WILLIAM SHAKESPEARE   \n1    DUCHESS OF NEWCASTLE MARGARET CAVENDISH   \n2                             THOMAS BASTARD   \n3                             EDMUND SPENSER   \n4                          RICHARD BARNFIELD   \n..                                       ...   \n568                            SARA TEASDALE   \n569                               HART CRANE   \n570                     WILLIAM BUTLER YEATS   \n571                            CARL SANDBURG   \n572                        RICHARD ALDINGTON   \n\n                                               content  \\\n0    Let the bird of loudest lay\\r\\nOn the sole Ara...   \n1    Sir Charles into my chamber coming in\\r\\nWhen ...   \n2    Our vice runs beyond all that old men saw\\r\\nA...   \n3    Lo I the man whose Muse whilome did maske\\r\\nA...   \n4    Long have I longd to see my love againe\\r\\nSti...   \n..                                                 ...   \n568  With the man I love who loves me not\\r\\nI walk...   \n569  Hart Crane Voyages I II III IV V VI from The C...   \n570  When you are old and grey and full of sleep\\r\\...   \n571  Give me hunger\\r\\nO you gods that sit and give...   \n572  Potuia potuia\\r\\nWhite grave goddess\\r\\nPity m...   \n\n                                   poem_name  age                  type  \n0                 The Phoenix and the Turtle    1  Mythology & Folklore  \n1                   An Epilogue to the Above    1  Mythology & Folklore  \n2                         Book 7, Epigram 42    1  Mythology & Folklore  \n3    from The Faerie Queene: Book I, Canto I    1  Mythology & Folklore  \n4                                  Sonnet 16    1  Mythology & Folklore  \n..                                       ...  ...                   ...  \n568                             Union Square    0                  Love  \n569                                  Voyages    0                  Love  \n570                         When You Are Old    0                  Love  \n571                              At a Window    0                  Love  \n572                        To a Greek Marble    0                  Love  \n\n[573 rows x 5 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>author</th>\n      <th>content</th>\n      <th>poem_name</th>\n      <th>age</th>\n      <th>type</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>WILLIAM SHAKESPEARE</td>\n      <td>Let the bird of loudest lay\\r\\nOn the sole Ara...</td>\n      <td>The Phoenix and the Turtle</td>\n      <td>1</td>\n      <td>Mythology &amp; Folklore</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>DUCHESS OF NEWCASTLE MARGARET CAVENDISH</td>\n      <td>Sir Charles into my chamber coming in\\r\\nWhen ...</td>\n      <td>An Epilogue to the Above</td>\n      <td>1</td>\n      <td>Mythology &amp; Folklore</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>THOMAS BASTARD</td>\n      <td>Our vice runs beyond all that old men saw\\r\\nA...</td>\n      <td>Book 7, Epigram 42</td>\n      <td>1</td>\n      <td>Mythology &amp; Folklore</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>EDMUND SPENSER</td>\n      <td>Lo I the man whose Muse whilome did maske\\r\\nA...</td>\n      <td>from The Faerie Queene: Book I, Canto I</td>\n      <td>1</td>\n      <td>Mythology &amp; Folklore</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>RICHARD BARNFIELD</td>\n      <td>Long have I longd to see my love againe\\r\\nSti...</td>\n      <td>Sonnet 16</td>\n      <td>1</td>\n      <td>Mythology &amp; Folklore</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>568</th>\n      <td>SARA TEASDALE</td>\n      <td>With the man I love who loves me not\\r\\nI walk...</td>\n      <td>Union Square</td>\n      <td>0</td>\n      <td>Love</td>\n    </tr>\n    <tr>\n      <th>569</th>\n      <td>HART CRANE</td>\n      <td>Hart Crane Voyages I II III IV V VI from The C...</td>\n      <td>Voyages</td>\n      <td>0</td>\n      <td>Love</td>\n    </tr>\n    <tr>\n      <th>570</th>\n      <td>WILLIAM BUTLER YEATS</td>\n      <td>When you are old and grey and full of sleep\\r\\...</td>\n      <td>When You Are Old</td>\n      <td>0</td>\n      <td>Love</td>\n    </tr>\n    <tr>\n      <th>571</th>\n      <td>CARL SANDBURG</td>\n      <td>Give me hunger\\r\\nO you gods that sit and give...</td>\n      <td>At a Window</td>\n      <td>0</td>\n      <td>Love</td>\n    </tr>\n    <tr>\n      <th>572</th>\n      <td>RICHARD ALDINGTON</td>\n      <td>Potuia potuia\\r\\nWhite grave goddess\\r\\nPity m...</td>\n      <td>To a Greek Marble</td>\n      <td>0</td>\n      <td>Love</td>\n    </tr>\n  </tbody>\n</table>\n<p>573 rows × 5 columns</p>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_poetry.drop(columns=[\"author\", \"poem_name\",\"type\"])","execution_count":11,"outputs":[{"output_type":"execute_result","execution_count":11,"data":{"text/plain":"                                               content  age\n0    Let the bird of loudest lay\\r\\nOn the sole Ara...    1\n1    Sir Charles into my chamber coming in\\r\\nWhen ...    1\n2    Our vice runs beyond all that old men saw\\r\\nA...    1\n3    Lo I the man whose Muse whilome did maske\\r\\nA...    1\n4    Long have I longd to see my love againe\\r\\nSti...    1\n..                                                 ...  ...\n568  With the man I love who loves me not\\r\\nI walk...    0\n569  Hart Crane Voyages I II III IV V VI from The C...    0\n570  When you are old and grey and full of sleep\\r\\...    0\n571  Give me hunger\\r\\nO you gods that sit and give...    0\n572  Potuia potuia\\r\\nWhite grave goddess\\r\\nPity m...    0\n\n[573 rows x 2 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>content</th>\n      <th>age</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Let the bird of loudest lay\\r\\nOn the sole Ara...</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Sir Charles into my chamber coming in\\r\\nWhen ...</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Our vice runs beyond all that old men saw\\r\\nA...</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Lo I the man whose Muse whilome did maske\\r\\nA...</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Long have I longd to see my love againe\\r\\nSti...</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>568</th>\n      <td>With the man I love who loves me not\\r\\nI walk...</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>569</th>\n      <td>Hart Crane Voyages I II III IV V VI from The C...</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>570</th>\n      <td>When you are old and grey and full of sleep\\r\\...</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>571</th>\n      <td>Give me hunger\\r\\nO you gods that sit and give...</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>572</th>\n      <td>Potuia potuia\\r\\nWhite grave goddess\\r\\nPity m...</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n<p>573 rows × 2 columns</p>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.preprocessing.text import Tokenizer\ntokenizer=Tokenizer(num_words=1009)\ntokenizer.fit_on_texts(df_poetry.content)\nsequences=tokenizer.texts_to_sequences(df_poetry.content)\ntokenized=tokenizer.texts_to_matrix(df_poetry.content)\nword_index=tokenizer.word_index\nprint(\"Found %s unique tokens.\"%len(word_index))","execution_count":12,"outputs":[{"output_type":"stream","text":"Using TensorFlow backend.\n","name":"stderr"},{"output_type":"stream","text":"Found 14170 unique tokens.\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"tokenized","execution_count":13,"outputs":[{"output_type":"execute_result","execution_count":13,"data":{"text/plain":"array([[0., 1., 1., ..., 0., 0., 0.],\n       [0., 1., 1., ..., 0., 0., 0.],\n       [0., 1., 1., ..., 0., 0., 0.],\n       ...,\n       [0., 1., 1., ..., 0., 0., 0.],\n       [0., 1., 1., ..., 0., 0., 0.],\n       [0., 1., 1., ..., 0., 0., 0.]])"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"tokenized.shape","execution_count":14,"outputs":[{"output_type":"execute_result","execution_count":14,"data":{"text/plain":"(573, 1009)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"markdown","source":"from sklearn.feature_extraction.text import TfidfVectorizer\nvectorizer = TfidfVectorizer()\nX = vectorizer.fit_transform(df_poetry.content)\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"X=tokenized\nY=df_poetry.age","execution_count":15,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tokenized.shape","execution_count":16,"outputs":[{"output_type":"execute_result","execution_count":16,"data":{"text/plain":"(573, 1009)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_poetry.age.shape","execution_count":17,"outputs":[{"output_type":"execute_result","execution_count":17,"data":{"text/plain":"(573,)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_test, y_train, y_test =train_test_split(X,Y,test_size=0.2)","execution_count":18,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train=tf.keras.preprocessing.sequence.pad_sequences(X_train, maxlen=300)\nX_test=tf.keras.preprocessing.sequence.pad_sequences(X_test, maxlen=300)","execution_count":19,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"max_features=10\ncallback = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=20)\nmodel = tf.keras.Sequential([Embedding(input_dim=100, output_dim=128),\n                            LSTM(64,activation='relu', dropout=0.05, return_sequences=True),\n                            LSTM(64, activation=\"relu\",dropout=0.05,recurrent_dropout=0.05, return_sequences=True),\n                            LSTM(32, activation=\"relu\",dropout=0.05,recurrent_dropout=0.05),\n                            Dense(2, activation=\"relu\"),\n                            Dense(1, activation=\"sigmoid\")])\nopt=tf.keras.optimizers.RMSprop()\nmodel.compile(optimizer=opt, loss=\"binary_crossentropy\", metrics=[\"acc\"])","execution_count":22,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(X_train, y_train.values, epochs=100, batch_size=40, validation_split=0.1, callbacks=[callback])","execution_count":23,"outputs":[{"output_type":"stream","text":"Train on 412 samples, validate on 46 samples\nEpoch 1/100\n412/412 [==============================] - 17s 40ms/sample - loss: 0.6927 - acc: 0.5388 - val_loss: 0.6928 - val_acc: 0.5217\nEpoch 2/100\n412/412 [==============================] - 9s 21ms/sample - loss: 0.6920 - acc: 0.5655 - val_loss: 0.6927 - val_acc: 0.5217\nEpoch 3/100\n412/412 [==============================] - 10s 23ms/sample - loss: 0.6916 - acc: 0.5655 - val_loss: 0.6926 - val_acc: 0.5217\nEpoch 4/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6913 - acc: 0.5655 - val_loss: 0.6926 - val_acc: 0.5217\nEpoch 5/100\n412/412 [==============================] - 9s 21ms/sample - loss: 0.6910 - acc: 0.5655 - val_loss: 0.6925 - val_acc: 0.5217\nEpoch 6/100\n412/412 [==============================] - 9s 21ms/sample - loss: 0.6906 - acc: 0.5655 - val_loss: 0.6924 - val_acc: 0.5217\nEpoch 7/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6904 - acc: 0.5655 - val_loss: 0.6924 - val_acc: 0.5217\nEpoch 8/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6900 - acc: 0.5655 - val_loss: 0.6923 - val_acc: 0.5217\nEpoch 9/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6898 - acc: 0.5655 - val_loss: 0.6923 - val_acc: 0.5217\nEpoch 10/100\n412/412 [==============================] - 9s 23ms/sample - loss: 0.6895 - acc: 0.5655 - val_loss: 0.6922 - val_acc: 0.5217\nEpoch 11/100\n412/412 [==============================] - 9s 23ms/sample - loss: 0.6892 - acc: 0.5655 - val_loss: 0.6922 - val_acc: 0.5217\nEpoch 12/100\n412/412 [==============================] - 9s 21ms/sample - loss: 0.6889 - acc: 0.5655 - val_loss: 0.6922 - val_acc: 0.5217\nEpoch 13/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6887 - acc: 0.5655 - val_loss: 0.6922 - val_acc: 0.5217\nEpoch 14/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6884 - acc: 0.5655 - val_loss: 0.6922 - val_acc: 0.5217\nEpoch 15/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6883 - acc: 0.5655 - val_loss: 0.6922 - val_acc: 0.5217\nEpoch 16/100\n412/412 [==============================] - 9s 23ms/sample - loss: 0.6880 - acc: 0.5655 - val_loss: 0.6922 - val_acc: 0.5217\nEpoch 17/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6878 - acc: 0.5655 - val_loss: 0.6922 - val_acc: 0.5217\nEpoch 18/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6876 - acc: 0.5655 - val_loss: 0.6923 - val_acc: 0.5217\nEpoch 19/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6874 - acc: 0.5655 - val_loss: 0.6923 - val_acc: 0.5217\nEpoch 20/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6872 - acc: 0.5655 - val_loss: 0.6923 - val_acc: 0.5217\nEpoch 21/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6871 - acc: 0.5655 - val_loss: 0.6924 - val_acc: 0.5217\nEpoch 22/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6869 - acc: 0.5655 - val_loss: 0.6924 - val_acc: 0.5217\nEpoch 23/100\n412/412 [==============================] - 9s 23ms/sample - loss: 0.6868 - acc: 0.5655 - val_loss: 0.6925 - val_acc: 0.5217\nEpoch 24/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6866 - acc: 0.5655 - val_loss: 0.6925 - val_acc: 0.5217\nEpoch 25/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6865 - acc: 0.5655 - val_loss: 0.6926 - val_acc: 0.5217\nEpoch 26/100\n412/412 [==============================] - 9s 21ms/sample - loss: 0.6863 - acc: 0.5655 - val_loss: 0.6926 - val_acc: 0.5217\nEpoch 27/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6862 - acc: 0.5655 - val_loss: 0.6927 - val_acc: 0.5217\nEpoch 28/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6862 - acc: 0.5655 - val_loss: 0.6927 - val_acc: 0.5217\nEpoch 29/100\n412/412 [==============================] - 9s 23ms/sample - loss: 0.6860 - acc: 0.5655 - val_loss: 0.6928 - val_acc: 0.5217\nEpoch 30/100\n412/412 [==============================] - 9s 23ms/sample - loss: 0.6859 - acc: 0.5655 - val_loss: 0.6929 - val_acc: 0.5217\nEpoch 31/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6859 - acc: 0.5655 - val_loss: 0.6929 - val_acc: 0.5217\nEpoch 32/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6857 - acc: 0.5655 - val_loss: 0.6930 - val_acc: 0.5217\nEpoch 33/100\n412/412 [==============================] - 9s 22ms/sample - loss: 0.6857 - acc: 0.5655 - val_loss: 0.6931 - val_acc: 0.5217\n","name":"stdout"},{"output_type":"execute_result","execution_count":23,"data":{"text/plain":"<tensorflow.python.keras.callbacks.History at 0x7fd1cc403f60>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.evaluate(X_test, y_test)","execution_count":24,"outputs":[{"output_type":"stream","text":"115/115 [==============================] - 1s 5ms/sample - loss: 0.6960 - acc: 0.5043\n","name":"stdout"},{"output_type":"execute_result","execution_count":24,"data":{"text/plain":"[0.6960138279458751, 0.5043478]"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_poetry=pd.read_csv(\"../input/poetry-analysis-with-machine-learning/all.csv\", sep=\",\")\ndf_poetry.head()","execution_count":25,"outputs":[{"output_type":"execute_result","execution_count":25,"data":{"text/plain":"                                    author  \\\n0                      WILLIAM SHAKESPEARE   \n1  DUCHESS OF NEWCASTLE MARGARET CAVENDISH   \n2                           THOMAS BASTARD   \n3                           EDMUND SPENSER   \n4                        RICHARD BARNFIELD   \n\n                                             content  \\\n0  Let the bird of loudest lay\\r\\nOn the sole Ara...   \n1  Sir Charles into my chamber coming in,\\r\\nWhen...   \n2  Our vice runs beyond all that old men saw,\\r\\n...   \n3  Lo I the man, whose Muse whilome did maske,\\r\\...   \n4  Long have I longd to see my love againe,\\r\\nSt...   \n\n                                 poem name          age                  type  \n0               The Phoenix and the Turtle  Renaissance  Mythology & Folklore  \n1                 An Epilogue to the Above  Renaissance  Mythology & Folklore  \n2                       Book 7, Epigram 42  Renaissance  Mythology & Folklore  \n3  from The Faerie Queene: Book I, Canto I  Renaissance  Mythology & Folklore  \n4                                Sonnet 16  Renaissance  Mythology & Folklore  ","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>author</th>\n      <th>content</th>\n      <th>poem name</th>\n      <th>age</th>\n      <th>type</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>WILLIAM SHAKESPEARE</td>\n      <td>Let the bird of loudest lay\\r\\nOn the sole Ara...</td>\n      <td>The Phoenix and the Turtle</td>\n      <td>Renaissance</td>\n      <td>Mythology &amp; Folklore</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>DUCHESS OF NEWCASTLE MARGARET CAVENDISH</td>\n      <td>Sir Charles into my chamber coming in,\\r\\nWhen...</td>\n      <td>An Epilogue to the Above</td>\n      <td>Renaissance</td>\n      <td>Mythology &amp; Folklore</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>THOMAS BASTARD</td>\n      <td>Our vice runs beyond all that old men saw,\\r\\n...</td>\n      <td>Book 7, Epigram 42</td>\n      <td>Renaissance</td>\n      <td>Mythology &amp; Folklore</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>EDMUND SPENSER</td>\n      <td>Lo I the man, whose Muse whilome did maske,\\r\\...</td>\n      <td>from The Faerie Queene: Book I, Canto I</td>\n      <td>Renaissance</td>\n      <td>Mythology &amp; Folklore</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>RICHARD BARNFIELD</td>\n      <td>Long have I longd to see my love againe,\\r\\nSt...</td>\n      <td>Sonnet 16</td>\n      <td>Renaissance</td>\n      <td>Mythology &amp; Folklore</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"**Most used 20 words**"},{"metadata":{"trusted":true},"cell_type":"code","source":"import plotly.graph_objects as go\nfrom plotly.offline import iplot\nwords = df_poetry['content'].str.split(expand=True).unstack().value_counts()\ndata = [go.Bar(\n            x = words.index.values[2:20],\n            y = words.values[2:20],\n            marker= dict(colorscale='RdBu',\n                         color = words.values[2:40]\n                        ),\n            text='Word counts'\n    )]\n\nlayout = go.Layout(\n    title='Most used words excluding stopwords'\n)\n\nfig = go.Figure(data=data, layout=layout)\n\niplot(fig, filename='basic-bar')","execution_count":26,"outputs":[{"output_type":"display_data","data":{"text/html":"        <script type=\"text/javascript\">\n        window.PlotlyConfig = {MathJaxConfig: 'local'};\n        if (window.MathJax) {MathJax.Hub.Config({SVG: {font: \"STIX-Web\"}});}\n        if (typeof require !== 'undefined') {\n        require.undef(\"plotly\");\n        requirejs.config({\n            paths: {\n                'plotly': ['https://cdn.plot.ly/plotly-latest.min']\n            }\n        });\n        require(['plotly'], function(Plotly) {\n            window._Plotly = Plotly;\n        });\n        }\n        </script>\n        "},"metadata":{}},{"output_type":"display_data","data":{"text/html":"<div>\n        \n        \n            <div id=\"62524f68-5e67-47c8-9e89-ed90aa64004e\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>\n            <script type=\"text/javascript\">\n                require([\"plotly\"], function(Plotly) {\n                    window.PLOTLYENV=window.PLOTLYENV || {};\n                    \n                if (document.getElementById(\"62524f68-5e67-47c8-9e89-ed90aa64004e\")) {\n                    Plotly.newPlot(\n                        '62524f68-5e67-47c8-9e89-ed90aa64004e',\n                        [{\"marker\": {\"color\": [1957, 1641, 1477, 1360, 1326, 1198, 983, 957, 800, 731, 714, 710, 569, 540, 536, 494, 481, 461, 441, 436, 435, 433, 430, 427, 406, 386, 381, 377, 364, 349, 346, 335, 333, 331, 320, 317, 314, 305], \"colorscale\": [[0.0, \"rgb(103,0,31)\"], [0.1, \"rgb(178,24,43)\"], [0.2, \"rgb(214,96,77)\"], [0.3, \"rgb(244,165,130)\"], [0.4, \"rgb(253,219,199)\"], [0.5, \"rgb(247,247,247)\"], [0.6, \"rgb(209,229,240)\"], [0.7, \"rgb(146,197,222)\"], [0.8, \"rgb(67,147,195)\"], [0.9, \"rgb(33,102,172)\"], [1.0, \"rgb(5,48,97)\"]]}, \"text\": \"Word counts\", \"type\": \"bar\", \"x\": [\"of\", \"to\", \"And\", \"I\", \"in\", \"a\", \"that\", \"my\", \"with\", \"her\", \"is\", \"The\", \"his\", \"all\", \"not\", \"by\", \"as\", \"for\"], \"y\": [1957, 1641, 1477, 1360, 1326, 1198, 983, 957, 800, 731, 714, 710, 569, 540, 536, 494, 481, 461]}],\n                        {\"template\": {\"data\": {\"bar\": [{\"error_x\": {\"color\": \"#2a3f5f\"}, \"error_y\": {\"color\": \"#2a3f5f\"}, \"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"bar\"}], \"barpolar\": [{\"marker\": {\"line\": {\"color\": \"#E5ECF6\", \"width\": 0.5}}, \"type\": \"barpolar\"}], \"carpet\": [{\"aaxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"baxis\": {\"endlinecolor\": \"#2a3f5f\", \"gridcolor\": \"white\", \"linecolor\": \"white\", \"minorgridcolor\": \"white\", \"startlinecolor\": \"#2a3f5f\"}, \"type\": \"carpet\"}], \"choropleth\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"choropleth\"}], \"contour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"contour\"}], \"contourcarpet\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"contourcarpet\"}], \"heatmap\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmap\"}], \"heatmapgl\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"heatmapgl\"}], \"histogram\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"histogram\"}], \"histogram2d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2d\"}], \"histogram2dcontour\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"histogram2dcontour\"}], \"mesh3d\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"type\": \"mesh3d\"}], \"parcoords\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"parcoords\"}], \"pie\": [{\"automargin\": true, \"type\": \"pie\"}], \"scatter\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter\"}], \"scatter3d\": [{\"line\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatter3d\"}], \"scattercarpet\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattercarpet\"}], \"scattergeo\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergeo\"}], \"scattergl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattergl\"}], \"scattermapbox\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scattermapbox\"}], \"scatterpolar\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolar\"}], \"scatterpolargl\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterpolargl\"}], \"scatterternary\": [{\"marker\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"type\": \"scatterternary\"}], \"surface\": [{\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}, \"colorscale\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"type\": \"surface\"}], \"table\": [{\"cells\": {\"fill\": {\"color\": \"#EBF0F8\"}, \"line\": {\"color\": \"white\"}}, \"header\": {\"fill\": {\"color\": \"#C8D4E3\"}, \"line\": {\"color\": \"white\"}}, \"type\": \"table\"}]}, \"layout\": {\"annotationdefaults\": {\"arrowcolor\": \"#2a3f5f\", \"arrowhead\": 0, \"arrowwidth\": 1}, \"coloraxis\": {\"colorbar\": {\"outlinewidth\": 0, \"ticks\": \"\"}}, \"colorscale\": {\"diverging\": [[0, \"#8e0152\"], [0.1, \"#c51b7d\"], [0.2, \"#de77ae\"], [0.3, \"#f1b6da\"], [0.4, \"#fde0ef\"], [0.5, \"#f7f7f7\"], [0.6, \"#e6f5d0\"], [0.7, \"#b8e186\"], [0.8, \"#7fbc41\"], [0.9, \"#4d9221\"], [1, \"#276419\"]], \"sequential\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]], \"sequentialminus\": [[0.0, \"#0d0887\"], [0.1111111111111111, \"#46039f\"], [0.2222222222222222, \"#7201a8\"], [0.3333333333333333, \"#9c179e\"], [0.4444444444444444, \"#bd3786\"], [0.5555555555555556, \"#d8576b\"], [0.6666666666666666, \"#ed7953\"], [0.7777777777777778, \"#fb9f3a\"], [0.8888888888888888, \"#fdca26\"], [1.0, \"#f0f921\"]]}, \"colorway\": [\"#636efa\", \"#EF553B\", \"#00cc96\", \"#ab63fa\", \"#FFA15A\", \"#19d3f3\", \"#FF6692\", \"#B6E880\", \"#FF97FF\", \"#FECB52\"], \"font\": {\"color\": \"#2a3f5f\"}, \"geo\": {\"bgcolor\": \"white\", \"lakecolor\": \"white\", \"landcolor\": \"#E5ECF6\", \"showlakes\": true, \"showland\": true, \"subunitcolor\": \"white\"}, \"hoverlabel\": {\"align\": \"left\"}, \"hovermode\": \"closest\", \"mapbox\": {\"style\": \"light\"}, \"paper_bgcolor\": \"white\", \"plot_bgcolor\": \"#E5ECF6\", \"polar\": {\"angularaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"radialaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"scene\": {\"xaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"yaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}, \"zaxis\": {\"backgroundcolor\": \"#E5ECF6\", \"gridcolor\": \"white\", \"gridwidth\": 2, \"linecolor\": \"white\", \"showbackground\": true, \"ticks\": \"\", \"zerolinecolor\": \"white\"}}, \"shapedefaults\": {\"line\": {\"color\": \"#2a3f5f\"}}, \"ternary\": {\"aaxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"baxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}, \"bgcolor\": \"#E5ECF6\", \"caxis\": {\"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\"}}, \"title\": {\"x\": 0.05}, \"xaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}, \"yaxis\": {\"automargin\": true, \"gridcolor\": \"white\", \"linecolor\": \"white\", \"ticks\": \"\", \"title\": {\"standoff\": 15}, \"zerolinecolor\": \"white\", \"zerolinewidth\": 2}}}, \"title\": {\"text\": \"Most used words excluding stopwords\"}},\n                        {\"responsive\": true}\n                    ).then(function(){\n                            \nvar gd = document.getElementById('62524f68-5e67-47c8-9e89-ed90aa64004e');\nvar x = new MutationObserver(function (mutations, observer) {{\n        var display = window.getComputedStyle(gd).display;\n        if (!display || display === 'none') {{\n            console.log([gd, 'removed!']);\n            Plotly.purge(gd);\n            observer.disconnect();\n        }}\n}});\n\n// Listen for the removal of the full notebook cells\nvar notebookContainer = gd.closest('#notebook-container');\nif (notebookContainer) {{\n    x.observe(notebookContainer, {childList: true});\n}}\n\n// Listen for the clearing of the current output cell\nvar outputEl = gd.closest('.output');\nif (outputEl) {{\n    x.observe(outputEl, {childList: true});\n}}\n\n                        })\n                };\n                });\n            </script>\n        </div>"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"**Creating word cloud from most used 100 words**"},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\ndef word_cloud(content, title):\n    wc = WordCloud(background_color='white', max_words=200,\n                  stopwords=STOPWORDS, max_font_size=50)\n    wc.generate(\" \".join(content))\n    plt.figure(figsize=(16, 13))\n    plt.title(title, fontsize=20)\n    plt.imshow(wc.recolor(colormap='Pastel2', random_state=42), alpha=0.98)\n    plt.axis('off')","execution_count":27,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"word_cloud(df_poetry.content, \"Word Cloud\")","execution_count":28,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 1152x936 with 1 Axes>","image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"metadata":{},"cell_type":"markdown","source":"I expect strong correlation between label encoded features."},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.preprocessing import LabelEncoder\nle = LabelEncoder()\ndf_poetry.type=le.fit_transform(df_poetry.type)\ndf_poetry.age=le.fit_transform(df_poetry.age)\ndf_poetry.author=le.fit_transform(df_poetry.author)","execution_count":29,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"corr = df_poetry.corr()\ncorr","execution_count":30,"outputs":[{"output_type":"execute_result","execution_count":30,"data":{"text/plain":"          author       age      type\nauthor  1.000000  0.287501 -0.146664\nage     0.287501  1.000000 -0.437088\ntype   -0.146664 -0.437088  1.000000","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>author</th>\n      <th>age</th>\n      <th>type</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>author</th>\n      <td>1.000000</td>\n      <td>0.287501</td>\n      <td>-0.146664</td>\n    </tr>\n    <tr>\n      <th>age</th>\n      <td>0.287501</td>\n      <td>1.000000</td>\n      <td>-0.437088</td>\n    </tr>\n    <tr>\n      <th>type</th>\n      <td>-0.146664</td>\n      <td>-0.437088</td>\n      <td>1.000000</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"Heat map between label encoded features."},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.heatmap(corr, \n        xticklabels=corr.columns,\n        yticklabels=corr.columns)","execution_count":31,"outputs":[{"output_type":"execute_result","execution_count":31,"data":{"text/plain":"<matplotlib.axes._subplots.AxesSubplot at 0x7fd173e007f0>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 2 Axes>","image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"metadata":{},"cell_type":"markdown","source":"Categorical plot to explain distribution of type and authors of poetry through the ages. It'd be better if the ages were given in years instead of two categories."},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.catplot(x=\"age\", y=\"author\",hue=\"type\", data=df_poetry);","execution_count":32,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 402.375x360 with 1 Axes>","image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"metadata":{},"cell_type":"markdown","source":"First I'll separate the dataset for training and test, then I'll vectorize both sets with TFIDF and Count Vectorizer, and then apply decision tree for classification."},{"metadata":{"trusted":true},"cell_type":"code","source":"y=df_poetry['author']\nx=df_poetry[\"content\"]\nX_train, X_test, y_train, y_test =train_test_split(x,y,test_size=0.33, random_state=50)\nprint(X_train)","execution_count":33,"outputs":[{"output_type":"stream","text":"526    [i carry your heart with me(i carry it in] Cop...\n63     Full fathom five thy father lies;\\r\\nOf his bo...\n158    Love is a sickness full of woes,\\r\\nAll remedi...\n248    No spring nor summer beauty hath such grace\\r\\...\n175    Come away, come away, death,\\r\\n    And in sad...\n                             ...                        \n70     How like a winter hath my absence been\\r\\nFrom...\n132    Stella, think not that I by verse seek fame,\\r...\n289    If thou survive my well-contented day,\\r\\nWhen...\n109    Ye tradefull Merchants that with weary toyle,\\...\n480    [Version 1: 1921]\\r\\nThe quick sparks on the g...\nName: content, Length: 383, dtype: object\n","name":"stdout"}]},{"metadata":{},"cell_type":"raw","source":"Trying to predict the author of the poem from the content. Used Count Vectorizer and Decision Tree Classifier with entropy."},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.feature_extraction.text import TfidfVectorizer\nvectorizer = TfidfVectorizer()\nvectrain = vectorizer.fit_transform(X_train)\nvectest = vectorizer.transform(X_test)","execution_count":34,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"vectest.shape","execution_count":35,"outputs":[{"output_type":"execute_result","execution_count":35,"data":{"text/plain":"(190, 9936)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train.shape","execution_count":36,"outputs":[{"output_type":"execute_result","execution_count":36,"data":{"text/plain":"(383,)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"dtclassifier=DecisionTreeClassifier(criterion=\"entropy\", max_depth=None)\ndtclassifier.fit(vectrain,y_train)\npreddt = dtclassifier.predict(vectest)","execution_count":37,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"accuracy= accuracy_score(preddt,y_test)\nprint(accuracy)","execution_count":38,"outputs":[{"output_type":"stream","text":"0.35789473684210527\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"Trying to predict the age of the poem from the content. Used Count Vectorizer and Decision Tree Classifier with entropy."},{"metadata":{"trusted":true},"cell_type":"code","source":"y=df_poetry['age']\nx=df_poetry[\"content\"]\nX_train, X_test, y_train, y_test =train_test_split(x,y,test_size=0.33, random_state=50)","execution_count":39,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"vectorizer = TfidfVectorizer()\nvectrain = vectorizer.fit_transform(X_train)\nvectest = vectorizer.transform(X_test)","execution_count":40,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dtclassifier=DecisionTreeClassifier(criterion=\"entropy\", max_depth=None)\ndtclassifier.fit(vectrain,y_train)\npreddt = dtclassifier.predict(vectest)","execution_count":41,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"accuracy= accuracy_score(preddt,y_test)\nprint(accuracy)","execution_count":42,"outputs":[{"output_type":"stream","text":"0.868421052631579\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"Trying to predict authors from rest of the features this time, I don't expect too much of an improvement. Used Tfidf vectorizer and decision tree with gini index as split criterion."},{"metadata":{"trusted":true},"cell_type":"code","source":"y=df_poetry['author']\nX=df_poetry.loc[:, df_poetry.columns!=\"author\"]\nX_train, X_test, y_train, y_test =train_test_split(x,y,test_size=0.33, random_state=50)","execution_count":43,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"vectorizer = TfidfVectorizer()\nvectrain = vectorizer.fit_transform(X_train)\nvectest = vectorizer.transform(X_test)","execution_count":44,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dtclassifier=DecisionTreeClassifier(criterion=\"gini\", max_depth=None)\ndtclassifier.fit(vectrain,y_train)\npreddt = dtclassifier.predict(vectest)","execution_count":45,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"accuracy= accuracy_score(preddt,y_test)\nprint(accuracy)","execution_count":46,"outputs":[{"output_type":"stream","text":"0.4\n","name":"stdout"}]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}


--------------------------------------------------------------------------------