![](\"wordnet.png\")
"
15 | ]
16 | }
17 | ],
18 | "metadata": {
19 | "kernelspec": {
20 | "display_name": "Python 3",
21 | "language": "python",
22 | "name": "python3"
23 | },
24 | "language_info": {
25 | "codemirror_mode": {
26 | "name": "ipython",
27 | "version": 3
28 | },
29 | "file_extension": ".py",
30 | "mimetype": "text/x-python",
31 | "name": "python",
32 | "nbconvert_exporter": "python",
33 | "pygments_lexer": "ipython3",
34 | "version": "3.7.7"
35 | }
36 | },
37 | "nbformat": 4,
38 | "nbformat_minor": 5
39 | }
40 |
--------------------------------------------------------------------------------
/Knowledge Graphs/tree.py:
--------------------------------------------------------------------------------
1 | # coding: utf-8
2 | from spacy_wordnet.wordnet_annotator import WordnetAnnotator
3 | from spacy import load
4 | from spacy_wordnet.wordnet_annotator import WordnetAnnotator
5 | import pandas as pd
6 | nlp = load('en_core_web_sm')
7 | nlp.add_pipe(WordnetAnnotator(nlp.lang))
8 | token = nlp('Calculator.')[0]
9 | token._.wordnet.synsets()
10 | meaning1, meaning2 = token = nlp('Calculator.')[0]
11 | meaning1, meaning2 = token._.wordnet.synsets()
12 | meaning1
13 | meaning1.name()
14 | meaning1.lemmas()
15 | meaning2.lemmas()
16 | token._.wordnet.wordnet_domains()
17 | nlp('mathematics')[0]._.wordnet.wordnet_domains()
18 | 'science' in _
19 | nlp('pure_science')[0]._.wordnet.wordnet_domains()
20 | nlp('science')[0]._.wordnet.wordnet_domains()
21 | wnet = nlp('science')[0]._.wordnet
22 | wnet.wordnet_synsets_for_domain()
23 | wnet.lemmas()
24 | token = nlp('human')[0]
25 | token._.wordnet.lemmas()
26 | token._.wordnet.synsets()
27 | [c.lemmas() for c in token._.wordnet.synsets()]
28 | syn =token._.wordnet.synsets()
29 | x = syn[0]
30 | x
31 | x.common_hypernyms()
32 | man = nlp('man')[0]
33 | woman = nlp('woman')[0]
34 | man._.wordnet.synsets()
35 | man_syn = man._.wordnet.synsets()[0]
36 | woman_syn = woman._.wordnet.synsets()[0]
37 | man_syn
38 | woman_syn
39 | man_syn.common_hypernyms(woman_syn)
40 | man_syn.entailments()
41 | get_ipython().run_line_magic('pinfo', 'man_syn.entailments')
42 | man_syn.examples()
43 | man_syn.hypernyms()
44 | woman_syn.hypernyms()
45 | man_syn.hyponyms()
46 | woman_syn.hyponyms()
47 | get_ipython().run_line_magic('pinfo', 'man_syn.jcn_similarity')
48 | get_ipython().run_line_magic('pinfo', 'man_syn.lemmas')
49 | man_syn.lemmas()
50 | get_ipython().run_line_magic('pinfo', 'man_syn.similar_tos')
51 | man_syn.similar_tos()
52 | while True:
53 | x = man_syn.hypernyms()[0]
54 | print(x)
55 | x = x.hypernyms()[0]
56 |
57 | x = man_syn
58 | while True:
59 | print(x)
60 | x = x.hypernyms()[0]
61 |
62 | x
63 | x.hypernyms()
64 | x = man_syn
65 | while True:
66 | print(x)
67 | x = x.hyponyms()[0]
68 |
69 | while True:
70 | print(x)
71 | i = 0
72 | try:
73 | x = x.hyponyms()[i]
74 | except IndexError:
75 | i += 1
76 | x = x.hyponyms()[i]
77 |
78 | while True:
79 | print(x)
80 | try:
81 | i = 0
82 | x = x.hyponyms()[i]
83 | except IndexError:
84 | i += 1
85 | x = x.hyponyms()[i]
86 |
87 |
88 |
--------------------------------------------------------------------------------
/distributional semantics/utils.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python
2 | # coding: utf-8
3 |
4 | # In[1]:
5 |
6 |
7 | from sklearn.decomposition import PCA
8 | from sklearn.manifold import TSNE
9 | import numpy as np
10 | import matplotlib.pyplot as plt
11 | from gensim.models.callbacks import CallbackAny2Vec
12 | from gensim.models import Word2Vec, KeyedVectors
13 | from tensorflow.keras.layers import Embedding
14 |
15 |
16 | class MetricCallback(CallbackAny2Vec):
17 | """
18 | Callback to print loss after each epoch
19 | """
20 | def __init__(self, every=10):
21 | self.myloss = []
22 | self.epoch = 0
23 | self.every = every
24 |
25 | def on_epoch_end(self, model):
26 | loss = model.get_latest_training_loss()
27 | if self.epoch == 0:
28 | self.myloss.append(loss)
29 | else:
30 | self.myloss.append(loss - self.loss_previous_step)
31 | if self.epoch % self.every == 0:
32 | print(f'Loss after epoch {self.epoch}: {self.myloss[-1]}') # NOQA: T001
33 | self.epoch += 1
34 | self.loss_previous_step = loss
35 |
36 |
37 | def plot_arrows(starts, ends, wv, estimator=PCA, **kwargs):
38 | if len(starts) != len(ends):
39 | raise ValueError('starts and ends must be the same length.')
40 | fig, ax = plt.subplots(figsize=kwargs.pop('figsize', (8, 8)))
41 | X = wv[starts + ends] # NOQA: N806
42 | x_red = estimator(n_components=2).fit_transform(X)
43 | plt.scatter(*x_red.T)
44 | for i, word in enumerate(starts + ends):
45 | plt.annotate(word, x_red[i])
46 | xstart = x_red[:len(starts)]
47 | xend = x_red[len(starts):]
48 | for i, (start, end) in enumerate(zip(starts, ends)):
49 | x1, y1 = xstart[i]
50 | x2, y2 = xend[i]
51 | plt.arrow(x1, y1, x2 - x1, y2 - y1)
52 |
53 |
54 | def plot_vectors(words, model, estimator=TSNE, **kwargs):
55 | names = []
56 | vectors = []
57 | for word in words:
58 | if word in model.wv:
59 | names.append(word)
60 | vectors.append(model.wv[word])
61 |
62 | X = np.r_[vectors] # NOQA: N806
63 | x_red = estimator(n_components=2).fit_transform(X)
64 | fig, ax = plt.subplots(figsize=kwargs.pop('figsize', (16, 16))) # NOQA: E912
65 | ax.scatter(*x_red.T)
66 |
67 | for i, word in enumerate(names):
68 | plt.annotate(word, x_red[i])
69 |
70 |
71 | def make_embedding_layer(model, tokenizer, MAX_SEQUENCE_LENGTH): # NOQA: N803
72 | word_index = tokenizer.word_index
73 | if isinstance(model, Word2Vec):
74 | wv = model.wv
75 | elif isinstance(model, KeyedVectors):
76 | wv = model
77 | embedding_matrix = np.zeros((len(word_index) + 1, wv.vector_size))
78 | for word, i in word_index.items():
79 | try:
80 | vector = wv.get_vector(word, False)
81 | embedding_matrix[i] = vector
82 | except KeyError:
83 | continue
84 | el = Embedding(
85 | len(word_index) + 1, wv.vector_size, weights=[embedding_matrix],
86 | input_length=MAX_SEQUENCE_LENGTH, trainable=False
87 | )
88 | return el
89 |
--------------------------------------------------------------------------------
/neural networks for NLP/imdb-reviews-classification.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "cells": [
3 | {
4 | "cell_type": "markdown",
5 | "id": "respective-webster",
6 | "metadata": {},
7 | "source": [
8 | "# Text Classification"
9 | ]
10 | },
11 | {
12 | "cell_type": "raw",
13 | "id": "adverse-evolution",
14 | "metadata": {},
15 | "source": [
16 | "----------------------------------------------------------------------\n",
17 | "Filename : imdb-reviews-classification.ipynb\n",
18 | "Author : Jaidev Deshpande\n",
19 | "Purpose : Understanding text classification using keras\n",
20 | "Libraries: tensorflow.keras, numpy, sklearn and pandas\n",
21 | "----------------------------------------------------------------------"
22 | ]
23 | },
24 | {
25 | "cell_type": "code",
26 | "execution_count": null,
27 | "id": "seasonal-balloon",
28 | "metadata": {},
29 | "outputs": [],
30 | "source": [
31 | "# Imports\n",
32 | "\n",
33 | "from tensorflow.keras.preprocessing import text_dataset_from_directory\n",
34 | "from tensorflow.keras import Sequential\n",
35 | "from tensorflow.keras.layers import Dense\n",
36 | "from tensorflow.keras.optimizers import SGD\n",
37 | "\n",
38 | "import pandas as pd\n",
39 | "import numpy as np\n",
40 | "from sklearn.feature_extraction.text import TfidfVectorizer\n",
41 | "from sklearn.model_selection import train_test_split\n",
42 | "import matplotlib.pyplot as plt\n",
43 | "%matplotlib inline"
44 | ]
45 | },
46 | {
47 | "cell_type": "markdown",
48 | "id": "corrected-railway",
49 | "metadata": {},
50 | "source": [
51 | "## The Problem: Large Movie Dataset Review\n",
52 | "### Classify movie reviews from IMDB into positive or negative sentiment.\n",
53 | "### Download the dataset [here](https://drive.google.com/drive/u/0/folders/1hYw0TQbwcM2YWEiKN-2c_kHCPtHO_TMC)"
54 | ]
55 | },
56 | {
57 | "cell_type": "code",
58 | "execution_count": null,
59 | "id": "fossil-vertical",
60 | "metadata": {},
61 | "outputs": [],
62 | "source": [
63 | "# Importing & preprocessing the dataset\n",
64 | "\n",
65 | "train_ds = text_dataset_from_directory('aclImdb/train')\n",
66 | "test_ds = text_dataset_from_directory('aclImdb/test')\n",
67 | "\n",
68 | "dfTrain = pd.DataFrame(train_ds.unbatch().as_numpy_iterator(), columns=['text', 'label'])\n",
69 | "dfTest = pd.DataFrame(test_ds.unbatch().as_numpy_iterator(), columns=['text', 'label'])\n",
70 | "_, xts = train_test_split(dfTest, stratify=dfTest['label'], test_size=0.25)"
71 | ]
72 | },
73 | {
74 | "cell_type": "code",
75 | "execution_count": null,
76 | "id": "vertical-northern",
77 | "metadata": {},
78 | "outputs": [],
79 | "source": [
80 | "# Look at a sample movie review\n",
81 | "\n",
82 | "print(dfTrain.loc[0, 'text'])"
83 | ]
84 | },
85 | {
86 | "cell_type": "code",
87 | "execution_count": null,
88 | "id": "virgin-illustration",
89 | "metadata": {},
90 | "outputs": [],
91 | "source": [
92 | "# Look at the label of the review\n",
93 | "\n",
94 | "dfTrain.loc[0, 'label']"
95 | ]
96 | },
97 | {
98 | "cell_type": "code",
99 | "execution_count": null,
100 | "id": "sustained-camcorder",
101 | "metadata": {},
102 | "outputs": [],
103 | "source": [
104 | "pd.options.display.max_colwidth = 100\n",
105 | "dfTrain.head()"
106 | ]
107 | },
108 | {
109 | "cell_type": "code",
110 | "execution_count": null,
111 | "id": "improved-negotiation",
112 | "metadata": {},
113 | "outputs": [],
114 | "source": [
115 | "dfTest.head()"
116 | ]
117 | },
118 | {
119 | "cell_type": "code",
120 | "execution_count": null,
121 | "id": "enormous-comment",
122 | "metadata": {},
123 | "outputs": [],
124 | "source": [
125 | "# Feature Extraction - Text to TFIDF\n",
126 | "\n",
127 | "vect = TfidfVectorizer(stop_words='english')\n",
128 | "XTrain = vect.fit_transform(dfTrain['text']).toarray()\n",
129 | "XTest = vect.transform(xts['text']).toarray()"
130 | ]
131 | },
132 | {
133 | "cell_type": "code",
134 | "execution_count": null,
135 | "id": "included-healing",
136 | "metadata": {},
137 | "outputs": [],
138 | "source": [
139 | "XTrain.shape"
140 | ]
141 | },
142 | {
143 | "cell_type": "code",
144 | "execution_count": null,
145 | "id": "according-russia",
146 | "metadata": {},
147 | "outputs": [],
148 | "source": [
149 | "# Assemble and compile the neural network\n",
150 | "\n",
151 | "model = Sequential([\n",
152 | " Dense(128, input_shape=(XTrain.shape[1],), activation='relu'),\n",
153 | " Dense(128, activation='relu'),\n",
154 | " Dense(64, activation='relu'),\n",
155 | " Dense(1, activation='sigmoid')\n",
156 | "])\n",
157 | "model.compile(loss='binary_crossentropy', optimizer=SGD(lr=1e-3), metrics=['accuracy'])"
158 | ]
159 | },
160 | {
161 | "cell_type": "code",
162 | "execution_count": null,
163 | "id": "protective-parking",
164 | "metadata": {
165 | "scrolled": true
166 | },
167 | "outputs": [],
168 | "source": [
169 | "# Train the neural network\n",
170 | "\n",
171 | "history = model.fit(XTrain, dfTrain['label'], batch_size=64, validation_data=(XTest, xts['label']), epochs=50)"
172 | ]
173 | },
174 | {
175 | "cell_type": "code",
176 | "execution_count": null,
177 | "id": "completed-poultry",
178 | "metadata": {},
179 | "outputs": [],
180 | "source": [
181 | "# Visualize the learning curve\n",
182 | "\n",
183 | "plt.plot(history.history['accuracy'], label='Train Accuracy')\n",
184 | "plt.plot(history.history['val_accuracy'], label='Test Accuracy')\n",
185 | "plt.legend()"
186 | ]
187 | },
188 | {
189 | "cell_type": "code",
190 | "execution_count": null,
191 | "id": "metallic-office",
192 | "metadata": {},
193 | "outputs": [],
194 | "source": []
195 | }
196 | ],
197 | "metadata": {
198 | "kernelspec": {
199 | "display_name": "Python 3",
200 | "language": "python",
201 | "name": "python3"
202 | },
203 | "language_info": {
204 | "codemirror_mode": {
205 | "name": "ipython",
206 | "version": 3
207 | },
208 | "file_extension": ".py",
209 | "mimetype": "text/x-python",
210 | "name": "python",
211 | "nbconvert_exporter": "python",
212 | "pygments_lexer": "ipython3",
213 | "version": "3.7.7"
214 | }
215 | },
216 | "nbformat": 4,
217 | "nbformat_minor": 5
218 | }
219 |
--------------------------------------------------------------------------------
/neural networks for NLP/keras.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "cells": [
3 | {
4 | "cell_type": "markdown",
5 | "id": "strange-seafood",
6 | "metadata": {},
7 | "source": [
8 | "## [Installing Tensorflow / Keras](https://www.tensorflow.org/install)"
9 | ]
10 | },
11 | {
12 | "cell_type": "code",
13 | "execution_count": null,
14 | "id": "aquatic-learning",
15 | "metadata": {},
16 | "outputs": [],
17 | "source": [
18 | "# Imports\n",
19 | "\n",
20 | "from tensorflow.keras.layers import Dense\n",
21 | "from tensorflow.keras import Sequential\n",
22 | "from tensorflow.keras.optimizers import SGD\n",
23 | "from tensorflow.keras.utils import to_categorical, plot_model\n",
24 | "import pandas as pd\n",
25 | "import numpy as np\n",
26 | "import matplotlib.pyplot as plt\n",
27 | "%matplotlib inline"
28 | ]
29 | },
30 | {
31 | "cell_type": "markdown",
32 | "id": "maritime-flavor",
33 | "metadata": {},
34 | "source": [
35 | "## Problem: **Credit Card Fraud Detection**\n",
36 | "### Given a list of 28 anonimyzed features and the amount of money involved in a credt card transaction, predict whether the transaction is likely to be fraudulent.\n",
37 | "### Source: https://www.kaggle.com/mlg-ulb/creditcardfraud/"
38 | ]
39 | },
40 | {
41 | "cell_type": "code",
42 | "execution_count": null,
43 | "id": "occupied-eagle",
44 | "metadata": {},
45 | "outputs": [],
46 | "source": [
47 | "# Preview dataset\n",
48 | "\n",
49 | "df = pd.read_csv('creditcard.csv')\n",
50 | "df.drop(['Time'], axis=1, inplace=True)\n",
51 | "df.head()"
52 | ]
53 | },
54 | {
55 | "cell_type": "code",
56 | "execution_count": null,
57 | "id": "stock-imperial",
58 | "metadata": {},
59 | "outputs": [],
60 | "source": [
61 | "print(len(df))"
62 | ]
63 | },
64 | {
65 | "cell_type": "code",
66 | "execution_count": null,
67 | "id": "charged-parade",
68 | "metadata": {},
69 | "outputs": [],
70 | "source": [
71 | "# Check the proportion of the classes\n",
72 | "\n",
73 | "df['Class'].value_counts(normalize=True)"
74 | ]
75 | },
76 | {
77 | "cell_type": "code",
78 | "execution_count": null,
79 | "id": "level-telephone",
80 | "metadata": {},
81 | "outputs": [],
82 | "source": [
83 | "df['Class'].value_counts(normalize=True).plot(kind='pie')"
84 | ]
85 | },
86 | {
87 | "cell_type": "code",
88 | "execution_count": null,
89 | "id": "attached-potter",
90 | "metadata": {},
91 | "outputs": [],
92 | "source": [
93 | "# Define the input and the output\n",
94 | "\n",
95 | "y = df.pop('Class').values\n",
96 | "X = df.values"
97 | ]
98 | },
99 | {
100 | "cell_type": "code",
101 | "execution_count": null,
102 | "id": "aging-cream",
103 | "metadata": {},
104 | "outputs": [],
105 | "source": [
106 | "# Assemble the network\n",
107 | "\n",
108 | "model = Sequential([\n",
109 | " Dense(16, input_shape=(29,), activation='relu'),\n",
110 | " Dense(8, activation='relu'),\n",
111 | " Dense(2, activation='softmax')\n",
112 | "])\n",
113 | "model.compile(loss='sparse_categorical_crossentropy', optimizer=SGD(lr=1e-3), metrics=['categorical_accuracy'])"
114 | ]
115 | },
116 | {
117 | "cell_type": "code",
118 | "execution_count": null,
119 | "id": "experienced-terminal",
120 | "metadata": {},
121 | "outputs": [],
122 | "source": [
123 | "# View the network - layer by layer\n",
124 | "\n",
125 | "plot_model(model, show_shapes=True, rankdir='LR')"
126 | ]
127 | },
128 | {
129 | "cell_type": "code",
130 | "execution_count": null,
131 | "id": "revolutionary-gothic",
132 | "metadata": {},
133 | "outputs": [],
134 | "source": [
135 | "model.layers"
136 | ]
137 | },
138 | {
139 | "cell_type": "code",
140 | "execution_count": null,
141 | "id": "authorized-holiday",
142 | "metadata": {},
143 | "outputs": [],
144 | "source": [
145 | "layer1, layer2, layer3 = model.layers"
146 | ]
147 | },
148 | {
149 | "cell_type": "code",
150 | "execution_count": null,
151 | "id": "quarterly-participation",
152 | "metadata": {},
153 | "outputs": [],
154 | "source": [
155 | "# View the shapes of weights and biases for each layer\n",
156 | "\n",
157 | "l1_weight, l1_bias = layer1.weights\n",
158 | "print(l1_weight.shape)\n",
159 | "print(l1_bias.shape)"
160 | ]
161 | },
162 | {
163 | "cell_type": "code",
164 | "execution_count": null,
165 | "id": "impaired-emphasis",
166 | "metadata": {},
167 | "outputs": [],
168 | "source": [
169 | "l2_weight, l2_bias = layer2.weights\n",
170 | "print(l2_weight.shape)\n",
171 | "print(l2_bias.shape)"
172 | ]
173 | },
174 | {
175 | "cell_type": "code",
176 | "execution_count": null,
177 | "id": "contained-leave",
178 | "metadata": {},
179 | "outputs": [],
180 | "source": [
181 | "l3_weight, l3_bias = layer3.weights\n",
182 | "print(l3_weight.shape)\n",
183 | "print(l3_bias.shape)"
184 | ]
185 | },
186 | {
187 | "cell_type": "code",
188 | "execution_count": null,
189 | "id": "ultimate-times",
190 | "metadata": {
191 | "scrolled": true
192 | },
193 | "outputs": [],
194 | "source": [
195 | "# Train the model\n",
196 | "\n",
197 | "history = model.fit(X, y, batch_size=128, epochs=30)"
198 | ]
199 | },
200 | {
201 | "cell_type": "code",
202 | "execution_count": null,
203 | "id": "signal-fireplace",
204 | "metadata": {},
205 | "outputs": [],
206 | "source": [
207 | "# Plot the loss across epochs\n",
208 | "\n",
209 | "plt.plot(history.history['loss'], label='Loss')"
210 | ]
211 | },
212 | {
213 | "cell_type": "code",
214 | "execution_count": null,
215 | "id": "advised-border",
216 | "metadata": {},
217 | "outputs": [],
218 | "source": [
219 | "# Plot the accuracy across epochs\n",
220 | "\n",
221 | "plt.plot(history.history['categorical_accuracy'], label='Accuracy')"
222 | ]
223 | },
224 | {
225 | "cell_type": "code",
226 | "execution_count": null,
227 | "id": "attended-mileage",
228 | "metadata": {},
229 | "outputs": [],
230 | "source": []
231 | }
232 | ],
233 | "metadata": {
234 | "kernelspec": {
235 | "display_name": "Python 3",
236 | "language": "python",
237 | "name": "python3"
238 | },
239 | "language_info": {
240 | "codemirror_mode": {
241 | "name": "ipython",
242 | "version": 3
243 | },
244 | "file_extension": ".py",
245 | "mimetype": "text/x-python",
246 | "name": "python",
247 | "nbconvert_exporter": "python",
248 | "pygments_lexer": "ipython3",
249 | "version": "3.7.7"
250 | }
251 | },
252 | "nbformat": 4,
253 | "nbformat_minor": 5
254 | }
255 |
--------------------------------------------------------------------------------
/neural networks for NLP/forward-pass.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "cells": [
3 | {
4 | "cell_type": "markdown",
5 | "id": "looking-election",
6 | "metadata": {},
7 | "source": [
8 | "# Forward Pass"
9 | ]
10 | },
11 | {
12 | "cell_type": "raw",
13 | "id": "continuous-royalty",
14 | "metadata": {},
15 | "source": [
16 | "----------------------------------------------------------------------\n",
17 | "Filename : forward-pass.ipynb\n",
18 | "Author : Jaidev Deshpande\n",
19 | "Content : Understanding feed forward propagation\n",
20 | "Libraries: numpy, sklearn and pandas\n",
21 | "----------------------------------------------------------------------"
22 | ]
23 | },
24 | {
25 | "cell_type": "code",
26 | "execution_count": null,
27 | "id": "understood-island",
28 | "metadata": {},
29 | "outputs": [],
30 | "source": [
31 | "# Importing libraries\n",
32 | "\n",
33 | "from sklearn.datasets import load_iris\n",
34 | "import pandas as pd\n",
35 | "import numpy as np"
36 | ]
37 | },
38 | {
39 | "cell_type": "code",
40 | "execution_count": null,
41 | "id": "spoken-clarity",
42 | "metadata": {},
43 | "outputs": [],
44 | "source": [
45 | "# Load the Iris dataset\n",
46 | "\n",
47 | "iris = load_iris()\n",
48 | "X = iris.data\n",
49 | "y = iris.target\n",
50 | "df = pd.DataFrame(X, columns=iris.feature_names)\n",
51 | "df['species'] = iris.target_names[y]\n",
52 | "df.sample(n=5)"
53 | ]
54 | },
55 | {
56 | "cell_type": "markdown",
57 | "id": "western-consensus",
58 | "metadata": {},
59 | "source": [
60 | "![](\"images/ann.png\")
"
61 | ]
62 | },
63 | {
64 | "cell_type": "code",
65 | "execution_count": null,
66 | "id": "detailed-nomination",
67 | "metadata": {},
68 | "outputs": [],
69 | "source": [
70 | "# Activation functions\n",
71 | "\n",
72 | "def sigmoid(x):\n",
73 | " return 1 / (1 + np.exp(-x))\n",
74 | "\n",
75 | "\n",
76 | "def softmax(x):\n",
77 | " return np.exp(x) / np.exp(x).sum()"
78 | ]
79 | },
80 | {
81 | "cell_type": "markdown",
82 | "id": "unable-typing",
83 | "metadata": {},
84 | "source": [
85 | "## Matrix Multiplication\n",
86 | "![](\"images/matmul.png\")
"
87 | ]
88 | },
89 | {
90 | "cell_type": "markdown",
91 | "id": "played-brighton",
92 | "metadata": {},
93 | "source": [
94 | "## Layer 1 Weights, Biases and Activation"
95 | ]
96 | },
97 | {
98 | "cell_type": "markdown",
99 | "id": "mounted-penetration",
100 | "metadata": {},
101 | "source": [
102 | ""
103 | ]
104 | },
105 | {
106 | "cell_type": "code",
107 | "execution_count": null,
108 | "id": "loving-metropolitan",
109 | "metadata": {},
110 | "outputs": [],
111 | "source": [
112 | "df.head()"
113 | ]
114 | },
115 | {
116 | "cell_type": "code",
117 | "execution_count": null,
118 | "id": "split-tension",
119 | "metadata": {},
120 | "outputs": [],
121 | "source": [
122 | "x = X[:5]\n",
123 | "x"
124 | ]
125 | },
126 | {
127 | "cell_type": "code",
128 | "execution_count": null,
129 | "id": "cross-finder",
130 | "metadata": {},
131 | "outputs": [],
132 | "source": [
133 | "# Initialize weights and biases\n",
134 | "\n",
135 | "w1 = np.random.rand(4, 5)\n",
136 | "b1 = np.random.rand(5)\n",
137 | "print(w1.shape)\n",
138 | "print(b1.shape)"
139 | ]
140 | },
141 | {
142 | "cell_type": "code",
143 | "execution_count": null,
144 | "id": "recorded-prison",
145 | "metadata": {},
146 | "outputs": [],
147 | "source": [
148 | "# Take a data sample\n",
149 | "\n",
150 | "sample = x[0]\n",
151 | "sample"
152 | ]
153 | },
154 | {
155 | "cell_type": "code",
156 | "execution_count": null,
157 | "id": "american-access",
158 | "metadata": {},
159 | "outputs": [],
160 | "source": [
161 | "print(w1)"
162 | ]
163 | },
164 | {
165 | "cell_type": "code",
166 | "execution_count": null,
167 | "id": "governing-reader",
168 | "metadata": {},
169 | "outputs": [],
170 | "source": [
171 | "# Multiply the sample with the first layer weights <𝐱,𝐰1>\n",
172 | "\n",
173 | "a1 = np.dot(sample, w1)\n",
174 | "a1"
175 | ]
176 | },
177 | {
178 | "cell_type": "code",
179 | "execution_count": null,
180 | "id": "concrete-differential",
181 | "metadata": {},
182 | "outputs": [],
183 | "source": [
184 | "b1"
185 | ]
186 | },
187 | {
188 | "cell_type": "code",
189 | "execution_count": null,
190 | "id": "institutional-talent",
191 | "metadata": {},
192 | "outputs": [],
193 | "source": [
194 | "# Add the bias to the product <𝐱,𝐰1>+ b\n",
195 | "\n",
196 | "a1 + b1"
197 | ]
198 | },
199 | {
200 | "cell_type": "code",
201 | "execution_count": null,
202 | "id": "balanced-storm",
203 | "metadata": {},
204 | "outputs": [],
205 | "source": [
206 | "# Apply the activation to get the output of the first layer f(<𝐱,𝐰1>+ b)\n",
207 | "\n",
208 | "f1 = sigmoid(a1 + b1)\n",
209 | "f1"
210 | ]
211 | },
212 | {
213 | "cell_type": "markdown",
214 | "id": "promising-exhibit",
215 | "metadata": {},
216 | "source": [
217 | "## Layer 2: Weights, Biases and Activations"
218 | ]
219 | },
220 | {
221 | "cell_type": "markdown",
222 | "id": "acknowledged-cruise",
223 | "metadata": {},
224 | "source": [
225 | ""
226 | ]
227 | },
228 | {
229 | "cell_type": "code",
230 | "execution_count": null,
231 | "id": "color-source",
232 | "metadata": {},
233 | "outputs": [],
234 | "source": [
235 | "w2 = np.random.rand(5, 7)\n",
236 | "b2 = np.random.rand(7)"
237 | ]
238 | },
239 | {
240 | "cell_type": "code",
241 | "execution_count": null,
242 | "id": "visible-fifth",
243 | "metadata": {},
244 | "outputs": [],
245 | "source": [
246 | "a2 = np.dot(f1, w2) + b2\n",
247 | "a2"
248 | ]
249 | },
250 | {
251 | "cell_type": "code",
252 | "execution_count": null,
253 | "id": "radical-serum",
254 | "metadata": {},
255 | "outputs": [],
256 | "source": [
257 | "f2 = sigmoid(a2)\n",
258 | "f2"
259 | ]
260 | },
261 | {
262 | "cell_type": "markdown",
263 | "id": "ahead-outreach",
264 | "metadata": {},
265 | "source": [
266 | "## Layer 3: Weights, Biases and Activations"
267 | ]
268 | },
269 | {
270 | "cell_type": "markdown",
271 | "id": "fuzzy-homeless",
272 | "metadata": {},
273 | "source": [
274 | ""
275 | ]
276 | },
277 | {
278 | "cell_type": "code",
279 | "execution_count": null,
280 | "id": "conventional-white",
281 | "metadata": {},
282 | "outputs": [],
283 | "source": [
284 | "w3 = np.random.rand(7, 3)\n",
285 | "b3 = np.random.rand(3)"
286 | ]
287 | },
288 | {
289 | "cell_type": "code",
290 | "execution_count": null,
291 | "id": "beautiful-springfield",
292 | "metadata": {},
293 | "outputs": [],
294 | "source": [
295 | "a3 = np.dot(f2, w3) + b3\n",
296 | "a3"
297 | ]
298 | },
299 | {
300 | "cell_type": "code",
301 | "execution_count": null,
302 | "id": "solid-inquiry",
303 | "metadata": {},
304 | "outputs": [],
305 | "source": [
306 | "f3 = softmax(a3)\n",
307 | "f3"
308 | ]
309 | },
310 | {
311 | "cell_type": "code",
312 | "execution_count": null,
313 | "id": "valuable-science",
314 | "metadata": {},
315 | "outputs": [],
316 | "source": []
317 | }
318 | ],
319 | "metadata": {
320 | "kernelspec": {
321 | "display_name": "Python 3",
322 | "language": "python",
323 | "name": "python3"
324 | },
325 | "language_info": {
326 | "codemirror_mode": {
327 | "name": "ipython",
328 | "version": 3
329 | },
330 | "file_extension": ".py",
331 | "mimetype": "text/x-python",
332 | "name": "python",
333 | "nbconvert_exporter": "python",
334 | "pygments_lexer": "ipython3",
335 | "version": "3.7.7"
336 | }
337 | },
338 | "nbformat": 4,
339 | "nbformat_minor": 5
340 | }
341 |
--------------------------------------------------------------------------------
/Knowledge Graphs/intro-to-wordnet.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "cells": [
3 | {
4 | "cell_type": "raw",
5 | "id": "freelance-naples",
6 | "metadata": {},
7 | "source": [
8 | "----------------------------------------------------------------------\n",
9 | "Filename : intro-to-wordnet.ipynb\n",
10 | "Author : Jaidev Deshpande\n",
11 | "Purpose : Understanding Wordnet functionalities\n",
12 | "Libraries: nltk\n",
13 | "----------------------------------------------------------------------"
14 | ]
15 | },
16 | {
17 | "cell_type": "markdown",
18 | "id": "anonymous-canadian",
19 | "metadata": {},
20 | "source": [
21 | "## [WordNet®](https://wordnet.princeton.edu/) Tutorial\n",
22 | "\n",
23 | "### Navigating Wornet Relationships"
24 | ]
25 | },
26 | {
27 | "cell_type": "code",
28 | "execution_count": 1,
29 | "id": "widespread-traveler",
30 | "metadata": {},
31 | "outputs": [
32 | {
33 | "name": "stdout",
34 | "output_type": "stream",
35 | "text": [
36 | "Requirement already satisfied: nltk in /home/jaidevd/anaconda3/lib/python3.7/site-packages (3.3)\n",
37 | "Requirement already satisfied: six in /home/jaidevd/anaconda3/lib/python3.7/site-packages (from nltk) (1.15.0)\n",
38 | "\u001b[33mWARNING: You are using pip version 21.0.1; however, version 21.1 is available.\n",
39 | "You should consider upgrading via the '/home/jaidevd/anaconda3/bin/python -m pip install --upgrade pip' command.\u001b[0m\n"
40 | ]
41 | }
42 | ],
43 | "source": [
44 | "!pip install nltk"
45 | ]
46 | },
47 | {
48 | "cell_type": "code",
49 | "execution_count": 2,
50 | "id": "vocational-clearance",
51 | "metadata": {},
52 | "outputs": [],
53 | "source": [
54 | "from nltk import download"
55 | ]
56 | },
57 | {
58 | "cell_type": "code",
59 | "execution_count": 3,
60 | "id": "sensitive-albany",
61 | "metadata": {},
62 | "outputs": [
63 | {
64 | "name": "stdout",
65 | "output_type": "stream",
66 | "text": [
67 | "[nltk_data] Downloading package wordnet to /home/jaidevd/nltk_data...\n",
68 | "[nltk_data] Package wordnet is already up-to-date!\n"
69 | ]
70 | },
71 | {
72 | "data": {
73 | "text/plain": [
74 | "True"
75 | ]
76 | },
77 | "execution_count": 3,
78 | "metadata": {},
79 | "output_type": "execute_result"
80 | }
81 | ],
82 | "source": [
83 | "download('wordnet')"
84 | ]
85 | },
86 | {
87 | "cell_type": "code",
88 | "execution_count": 4,
89 | "id": "weird-memory",
90 | "metadata": {},
91 | "outputs": [],
92 | "source": [
93 | "from nltk.corpus import wordnet"
94 | ]
95 | },
96 | {
97 | "cell_type": "code",
98 | "execution_count": 5,
99 | "id": "developing-failure",
100 | "metadata": {},
101 | "outputs": [
102 | {
103 | "data": {
104 | "text/plain": [
105 | "[Synset('tractor.n.01'), Synset('tractor.n.02')]"
106 | ]
107 | },
108 | "execution_count": 5,
109 | "metadata": {},
110 | "output_type": "execute_result"
111 | }
112 | ],
113 | "source": [
114 | "# Synsets\n",
115 | "\n",
116 | "tractor = wordnet.synsets('tractor')\n",
117 | "tractor"
118 | ]
119 | },
120 | {
121 | "cell_type": "code",
122 | "execution_count": 6,
123 | "id": "seasonal-hungary",
124 | "metadata": {},
125 | "outputs": [
126 | {
127 | "data": {
128 | "text/plain": [
129 | "['a wheeled vehicle with large wheels; used in farming and other applications',\n",
130 | " 'a truck that has a cab but no body; used for pulling large trailers or vans']"
131 | ]
132 | },
133 | "execution_count": 6,
134 | "metadata": {},
135 | "output_type": "execute_result"
136 | }
137 | ],
138 | "source": [
139 | "# Definitions of senses\n",
140 | "\n",
141 | "[syn.definition() for syn in tractor]"
142 | ]
143 | },
144 | {
145 | "cell_type": "code",
146 | "execution_count": 7,
147 | "id": "active-norwegian",
148 | "metadata": {},
149 | "outputs": [
150 | {
151 | "data": {
152 | "text/plain": [
153 | "[Synset('self-propelled_vehicle.n.01')]"
154 | ]
155 | },
156 | "execution_count": 7,
157 | "metadata": {},
158 | "output_type": "execute_result"
159 | }
160 | ],
161 | "source": [
162 | "# Hypernyms: Relation between a concept and its superordinate\n",
163 | "\n",
164 | "tractor = wordnet.synset('tractor.n.01')\n",
165 | "tractor.hypernyms()"
166 | ]
167 | },
168 | {
169 | "cell_type": "code",
170 | "execution_count": 8,
171 | "id": "arctic-customer",
172 | "metadata": {},
173 | "outputs": [
174 | {
175 | "data": {
176 | "text/plain": [
177 | "[Synset('wheeled_vehicle.n.01')]"
178 | ]
179 | },
180 | "execution_count": 8,
181 | "metadata": {},
182 | "output_type": "execute_result"
183 | }
184 | ],
185 | "source": [
186 | "self_propelled_vehicle = wordnet.synset('self-propelled_vehicle.n.01')\n",
187 | "self_propelled_vehicle.hypernyms()"
188 | ]
189 | },
190 | {
191 | "cell_type": "code",
192 | "execution_count": 9,
193 | "id": "invalid-lease",
194 | "metadata": {},
195 | "outputs": [
196 | {
197 | "data": {
198 | "text/plain": [
199 | "[Synset('axle.n.01'),\n",
200 | " Synset('brake.n.01'),\n",
201 | " Synset('splasher.n.01'),\n",
202 | " Synset('wheel.n.01')]"
203 | ]
204 | },
205 | "execution_count": 9,
206 | "metadata": {},
207 | "output_type": "execute_result"
208 | }
209 | ],
210 | "source": [
211 | "# Meronyms: Relation between a part and its whole\n",
212 | "\n",
213 | "wheeled_vehicle = wordnet.synset('wheeled_vehicle.n.01')\n",
214 | "wheeled_vehicle.part_meronyms()"
215 | ]
216 | },
217 | {
218 | "cell_type": "code",
219 | "execution_count": 10,
220 | "id": "brown-weekend",
221 | "metadata": {},
222 | "outputs": [
223 | {
224 | "data": {
225 | "text/plain": [
226 | "[Synset('baby_buggy.n.01'),\n",
227 | " Synset('bicycle.n.01'),\n",
228 | " Synset('boneshaker.n.01'),\n",
229 | " Synset('car.n.02'),\n",
230 | " Synset('handcart.n.01'),\n",
231 | " Synset('horse-drawn_vehicle.n.01'),\n",
232 | " Synset('motor_scooter.n.01'),\n",
233 | " Synset('rolling_stock.n.01'),\n",
234 | " Synset('scooter.n.02'),\n",
235 | " Synset('self-propelled_vehicle.n.01'),\n",
236 | " Synset('skateboard.n.01'),\n",
237 | " Synset('trailer.n.04'),\n",
238 | " Synset('tricycle.n.01'),\n",
239 | " Synset('unicycle.n.01'),\n",
240 | " Synset('wagon.n.01'),\n",
241 | " Synset('wagon.n.04'),\n",
242 | " Synset('welcome_wagon.n.01')]"
243 | ]
244 | },
245 | "execution_count": 10,
246 | "metadata": {},
247 | "output_type": "execute_result"
248 | }
249 | ],
250 | "source": [
251 | "# Hyponyms: Relation between a concept and its subordinate\n",
252 | "\n",
253 | "wheeled_vehicle.hyponyms()"
254 | ]
255 | },
256 | {
257 | "cell_type": "code",
258 | "execution_count": 11,
259 | "id": "theoretical-bargain",
260 | "metadata": {},
261 | "outputs": [
262 | {
263 | "data": {
264 | "text/plain": [
265 | "[Synset('wheeled_vehicle.n.01')]"
266 | ]
267 | },
268 | "execution_count": 11,
269 | "metadata": {},
270 | "output_type": "execute_result"
271 | }
272 | ],
273 | "source": [
274 | "# Holonyms: Relation between whole and its parts\n",
275 | "\n",
276 | "axle = wordnet.synset('axle.n.01')\n",
277 | "axle.part_holonyms()"
278 | ]
279 | },
280 | {
281 | "cell_type": "code",
282 | "execution_count": 12,
283 | "id": "identical-shoulder",
284 | "metadata": {},
285 | "outputs": [
286 | {
287 | "data": {
288 | "text/plain": [
289 | "[Synset('armored_vehicle.n.01'),\n",
290 | " Synset('carrier.n.02'),\n",
291 | " Synset('forklift.n.01'),\n",
292 | " Synset('locomotive.n.01'),\n",
293 | " Synset('motor_vehicle.n.01'),\n",
294 | " Synset('personnel_carrier.n.01'),\n",
295 | " Synset('reconnaissance_vehicle.n.01'),\n",
296 | " Synset('recreational_vehicle.n.01'),\n",
297 | " Synset('streetcar.n.01'),\n",
298 | " Synset('tracked_vehicle.n.01'),\n",
299 | " Synset('tractor.n.01'),\n",
300 | " Synset('weapons_carrier.n.01')]"
301 | ]
302 | },
303 | "execution_count": 12,
304 | "metadata": {},
305 | "output_type": "execute_result"
306 | }
307 | ],
308 | "source": [
309 | "self_propelled_vehicle.hyponyms()"
310 | ]
311 | },
312 | {
313 | "cell_type": "code",
314 | "execution_count": 13,
315 | "id": "quick-strengthening",
316 | "metadata": {},
317 | "outputs": [
318 | {
319 | "data": {
320 | "text/plain": [
321 | "[Synset('amphibian.n.01'),\n",
322 | " Synset('bloodmobile.n.01'),\n",
323 | " Synset('car.n.01'),\n",
324 | " Synset('doodlebug.n.01'),\n",
325 | " Synset('four-wheel_drive.n.01'),\n",
326 | " Synset('go-kart.n.01'),\n",
327 | " Synset('golfcart.n.01'),\n",
328 | " Synset('hearse.n.01'),\n",
329 | " Synset('motorcycle.n.01'),\n",
330 | " Synset('snowplow.n.01'),\n",
331 | " Synset('truck.n.01')]"
332 | ]
333 | },
334 | "execution_count": 13,
335 | "metadata": {},
336 | "output_type": "execute_result"
337 | }
338 | ],
339 | "source": [
340 | "motor_vehicle = wordnet.synset('motor_vehicle.n.01')\n",
341 | "motor_vehicle.hyponyms()"
342 | ]
343 | },
344 | {
345 | "cell_type": "code",
346 | "execution_count": 14,
347 | "id": "egyptian-appliance",
348 | "metadata": {},
349 | "outputs": [
350 | {
351 | "data": {
352 | "text/plain": [
353 | "[Synset('accelerator.n.01'),\n",
354 | " Synset('air_bag.n.01'),\n",
355 | " Synset('auto_accessory.n.01'),\n",
356 | " Synset('automobile_engine.n.01'),\n",
357 | " Synset('automobile_horn.n.01'),\n",
358 | " Synset('buffer.n.06'),\n",
359 | " Synset('bumper.n.02'),\n",
360 | " Synset('car_door.n.01'),\n",
361 | " Synset('car_mirror.n.01'),\n",
362 | " Synset('car_seat.n.01'),\n",
363 | " Synset('car_window.n.01'),\n",
364 | " Synset('fender.n.01'),\n",
365 | " Synset('first_gear.n.01'),\n",
366 | " Synset('floorboard.n.02'),\n",
367 | " Synset('gasoline_engine.n.01'),\n",
368 | " Synset('glove_compartment.n.01'),\n",
369 | " Synset('grille.n.02'),\n",
370 | " Synset('high_gear.n.01'),\n",
371 | " Synset('hood.n.09'),\n",
372 | " Synset('luggage_compartment.n.01'),\n",
373 | " Synset('rear_window.n.01'),\n",
374 | " Synset('reverse.n.02'),\n",
375 | " Synset('roof.n.02'),\n",
376 | " Synset('running_board.n.01'),\n",
377 | " Synset('stabilizer_bar.n.01'),\n",
378 | " Synset('sunroof.n.01'),\n",
379 | " Synset('tail_fin.n.02'),\n",
380 | " Synset('third_gear.n.01'),\n",
381 | " Synset('window.n.02')]"
382 | ]
383 | },
384 | "execution_count": 14,
385 | "metadata": {},
386 | "output_type": "execute_result"
387 | }
388 | ],
389 | "source": [
390 | "car = wordnet.synset('car.n.01')\n",
391 | "car.part_meronyms()"
392 | ]
393 | },
394 | {
395 | "cell_type": "code",
396 | "execution_count": null,
397 | "id": "civic-worst",
398 | "metadata": {},
399 | "outputs": [],
400 | "source": []
401 | }
402 | ],
403 | "metadata": {
404 | "kernelspec": {
405 | "display_name": "Python 3",
406 | "language": "python",
407 | "name": "python3"
408 | },
409 | "language_info": {
410 | "codemirror_mode": {
411 | "name": "ipython",
412 | "version": 3
413 | },
414 | "file_extension": ".py",
415 | "mimetype": "text/x-python",
416 | "name": "python",
417 | "nbconvert_exporter": "python",
418 | "pygments_lexer": "ipython3",
419 | "version": "3.7.7"
420 | }
421 | },
422 | "nbformat": 4,
423 | "nbformat_minor": 5
424 | }
425 |
--------------------------------------------------------------------------------
/Knowledge Graphs/lesk.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "cells": [
3 | {
4 | "cell_type": "markdown",
5 | "id": "shaped-norway",
6 | "metadata": {},
7 | "source": [
8 | "## Word-Sense Disambiguation"
9 | ]
10 | },
11 | {
12 | "cell_type": "code",
13 | "execution_count": 1,
14 | "id": "genetic-terror",
15 | "metadata": {},
16 | "outputs": [],
17 | "source": [
18 | "from nltk.corpus import wordnet as wn\n",
19 | "from nltk import wsd"
20 | ]
21 | },
22 | {
23 | "cell_type": "code",
24 | "execution_count": 2,
25 | "id": "adult-bangladesh",
26 | "metadata": {},
27 | "outputs": [],
28 | "source": [
29 | "X = 'The die is cast.'\n",
30 | "Y = 'Roll the die to get a 6.'\n",
31 | "Z = 'What is dead may never die.'"
32 | ]
33 | },
34 | {
35 | "cell_type": "code",
36 | "execution_count": 3,
37 | "id": "antique-burlington",
38 | "metadata": {},
39 | "outputs": [
40 | {
41 | "data": {
42 | "text/plain": [
43 | "[Synset('die.n.01'),\n",
44 | " Synset('die.n.02'),\n",
45 | " Synset('die.n.03'),\n",
46 | " Synset('die.v.01'),\n",
47 | " Synset('die.v.02'),\n",
48 | " Synset('die.v.03'),\n",
49 | " Synset('fail.v.04'),\n",
50 | " Synset('die.v.05'),\n",
51 | " Synset('die.v.06'),\n",
52 | " Synset('die.v.07'),\n",
53 | " Synset('die.v.08'),\n",
54 | " Synset('die.v.09'),\n",
55 | " Synset('die.v.10'),\n",
56 | " Synset('die.v.11')]"
57 | ]
58 | },
59 | "execution_count": 3,
60 | "metadata": {},
61 | "output_type": "execute_result"
62 | }
63 | ],
64 | "source": [
65 | "wn.synsets('die')"
66 | ]
67 | },
68 | {
69 | "cell_type": "code",
70 | "execution_count": 4,
71 | "id": "governing-montana",
72 | "metadata": {},
73 | "outputs": [
74 | {
75 | "data": {
76 | "text/plain": [
77 | "[Synset('die.n.01'), Synset('die.n.02'), Synset('die.n.03')]"
78 | ]
79 | },
80 | "execution_count": 4,
81 | "metadata": {},
82 | "output_type": "execute_result"
83 | }
84 | ],
85 | "source": [
86 | "wn.synsets('die', pos=wn.NOUN)"
87 | ]
88 | },
89 | {
90 | "cell_type": "code",
91 | "execution_count": 5,
92 | "id": "located-bookmark",
93 | "metadata": {},
94 | "outputs": [
95 | {
96 | "name": "stdout",
97 | "output_type": "stream",
98 | "text": [
99 | "a small cube with 1 to 6 spots on the six faces; used in gambling to generate random numbers\n",
100 | "a device used for shaping metal\n",
101 | "a cutting tool that is fitted into a diestock and used for cutting male (external) screw threads on screws or bolts or pipes or rods\n"
102 | ]
103 | }
104 | ],
105 | "source": [
106 | "for syn in wn.synsets('die', pos=wn.NOUN):\n",
107 | " print(syn.definition())"
108 | ]
109 | },
110 | {
111 | "cell_type": "code",
112 | "execution_count": 6,
113 | "id": "after-party",
114 | "metadata": {},
115 | "outputs": [
116 | {
117 | "name": "stdout",
118 | "output_type": "stream",
119 | "text": [
120 | "pass from physical life and lose all bodily attributes and functions necessary to sustain life\n",
121 | "suffer or face the pain of death\n",
122 | "be brought to or as if to the point of death by an intense emotion such as embarrassment, amusement, or shame\n",
123 | "stop operating or functioning\n",
124 | "feel indifferent towards\n",
125 | "languish as with love or desire\n",
126 | "cut or shape with a die\n",
127 | "to be on base at the end of an inning, of a player\n",
128 | "lose sparkle or bouquet\n",
129 | "disappear or come to an end\n",
130 | "suffer spiritual death; be damned (in the religious sense)\n"
131 | ]
132 | }
133 | ],
134 | "source": [
135 | "for syn in wn.synsets('die', pos=wn.VERB):\n",
136 | " print(syn.definition())"
137 | ]
138 | },
139 | {
140 | "cell_type": "markdown",
141 | "id": "bacterial-effect",
142 | "metadata": {},
143 | "source": [
144 | "## Word-Sense Disambiguation with Lesk Algorithm"
145 | ]
146 | },
147 | {
148 | "cell_type": "code",
149 | "execution_count": 7,
150 | "id": "threaded-tourism",
151 | "metadata": {},
152 | "outputs": [
153 | {
154 | "name": "stdout",
155 | "output_type": "stream",
156 | "text": [
157 | "The die is cast.\n"
158 | ]
159 | },
160 | {
161 | "data": {
162 | "text/plain": [
163 | "Synset('die.v.07')"
164 | ]
165 | },
166 | "execution_count": 7,
167 | "metadata": {},
168 | "output_type": "execute_result"
169 | }
170 | ],
171 | "source": [
172 | "print(X)\n",
173 | "wsd.lesk(X.split(), 'die')"
174 | ]
175 | },
176 | {
177 | "cell_type": "code",
178 | "execution_count": 8,
179 | "id": "fluid-cargo",
180 | "metadata": {},
181 | "outputs": [
182 | {
183 | "data": {
184 | "text/plain": [
185 | "'cut or shape with a die'"
186 | ]
187 | },
188 | "execution_count": 8,
189 | "metadata": {},
190 | "output_type": "execute_result"
191 | }
192 | ],
193 | "source": [
194 | "_.definition()"
195 | ]
196 | },
197 | {
198 | "cell_type": "code",
199 | "execution_count": 9,
200 | "id": "independent-melissa",
201 | "metadata": {},
202 | "outputs": [
203 | {
204 | "data": {
205 | "text/plain": [
206 | "'a cutting tool that is fitted into a diestock and used for cutting male (external) screw threads on screws or bolts or pipes or rods'"
207 | ]
208 | },
209 | "execution_count": 9,
210 | "metadata": {},
211 | "output_type": "execute_result"
212 | }
213 | ],
214 | "source": [
215 | "wsd.lesk(X.split(), 'die', pos=wn.NOUN).definition()"
216 | ]
217 | },
218 | {
219 | "cell_type": "code",
220 | "execution_count": 10,
221 | "id": "progressive-origin",
222 | "metadata": {},
223 | "outputs": [
224 | {
225 | "name": "stdout",
226 | "output_type": "stream",
227 | "text": [
228 | "Roll the die to get a 6.\n"
229 | ]
230 | },
231 | {
232 | "data": {
233 | "text/plain": [
234 | "'to be on base at the end of an inning, of a player'"
235 | ]
236 | },
237 | "execution_count": 10,
238 | "metadata": {},
239 | "output_type": "execute_result"
240 | }
241 | ],
242 | "source": [
243 | "print(Y)\n",
244 | "wsd.lesk(Y.split(), 'die').definition()"
245 | ]
246 | },
247 | {
248 | "cell_type": "code",
249 | "execution_count": 11,
250 | "id": "proof-while",
251 | "metadata": {},
252 | "outputs": [
253 | {
254 | "data": {
255 | "text/plain": [
256 | "'a small cube with 1 to 6 spots on the six faces; used in gambling to generate random numbers'"
257 | ]
258 | },
259 | "execution_count": 11,
260 | "metadata": {},
261 | "output_type": "execute_result"
262 | }
263 | ],
264 | "source": [
265 | "wsd.lesk(Y.split(), 'die', pos=wn.NOUN).definition()"
266 | ]
267 | },
268 | {
269 | "cell_type": "code",
270 | "execution_count": 12,
271 | "id": "middle-object",
272 | "metadata": {},
273 | "outputs": [
274 | {
275 | "name": "stdout",
276 | "output_type": "stream",
277 | "text": [
278 | "What is dead may never die.\n"
279 | ]
280 | },
281 | {
282 | "data": {
283 | "text/plain": [
284 | "'a cutting tool that is fitted into a diestock and used for cutting male (external) screw threads on screws or bolts or pipes or rods'"
285 | ]
286 | },
287 | "execution_count": 12,
288 | "metadata": {},
289 | "output_type": "execute_result"
290 | }
291 | ],
292 | "source": [
293 | "print(Z)\n",
294 | "wsd.lesk(Z.split(), 'die').definition()"
295 | ]
296 | },
297 | {
298 | "cell_type": "code",
299 | "execution_count": 13,
300 | "id": "organizational-joint",
301 | "metadata": {},
302 | "outputs": [
303 | {
304 | "data": {
305 | "text/plain": [
306 | "'stop operating or functioning'"
307 | ]
308 | },
309 | "execution_count": 13,
310 | "metadata": {},
311 | "output_type": "execute_result"
312 | }
313 | ],
314 | "source": [
315 | "wsd.lesk(Z.split(), 'die', pos=wn.VERB).definition()"
316 | ]
317 | },
318 | {
319 | "cell_type": "markdown",
320 | "id": "valuable-harbor",
321 | "metadata": {},
322 | "source": [
323 | "## Automatic POS Tagging + Lesk with spaCy"
324 | ]
325 | },
326 | {
327 | "cell_type": "code",
328 | "execution_count": null,
329 | "id": "defensive-trailer",
330 | "metadata": {},
331 | "outputs": [],
332 | "source": [
333 | "!pip install spacy"
334 | ]
335 | },
336 | {
337 | "cell_type": "code",
338 | "execution_count": 34,
339 | "id": "cellular-reflection",
340 | "metadata": {},
341 | "outputs": [],
342 | "source": [
343 | "from spacy.cli import download\n",
344 | "from spacy import load\n",
345 | "# download('en_core_web_sm')\n",
346 | "nlp = load('en_core_web_sm')"
347 | ]
348 | },
349 | {
350 | "cell_type": "code",
351 | "execution_count": 35,
352 | "id": "radical-melbourne",
353 | "metadata": {},
354 | "outputs": [],
355 | "source": [
356 | "import warnings\n",
357 | "\n",
358 | "POS_MAP = {\n",
359 | " 'VERB': wn.VERB,\n",
360 | " 'NOUN': wn.NOUN,\n",
361 | " 'PROPN': wn.NOUN\n",
362 | "}\n",
363 | "\n",
364 | "\n",
365 | "def lesk(doc, word):\n",
366 | " found = False\n",
367 | " for token in doc:\n",
368 | " if token.text == word:\n",
369 | " word = token\n",
370 | " found = True\n",
371 | " break\n",
372 | " if not found:\n",
373 | " raise ValueError(f'Word \\\"{word}\\\" does not appear in the document: {doc.text}.')\n",
374 | " pos = POS_MAP.get(word.pos_, False)\n",
375 | " if not pos:\n",
376 | " warnings.warn(f'POS tag for {word.text} not found in wordnet. Falling back to default Lesk behaviour.')\n",
377 | " args = [c.text for c in doc], word.text\n",
378 | " kwargs = dict(pos=pos)\n",
379 | " return wsd.lesk(*args, **kwargs)"
380 | ]
381 | },
382 | {
383 | "cell_type": "code",
384 | "execution_count": 36,
385 | "id": "monetary-disaster",
386 | "metadata": {},
387 | "outputs": [],
388 | "source": [
389 | "doc = nlp('Roll the die to get a 6.')"
390 | ]
391 | },
392 | {
393 | "cell_type": "code",
394 | "execution_count": 37,
395 | "id": "surgical-chrome",
396 | "metadata": {},
397 | "outputs": [
398 | {
399 | "data": {
400 | "text/plain": [
401 | "Synset('die.n.01')"
402 | ]
403 | },
404 | "execution_count": 37,
405 | "metadata": {},
406 | "output_type": "execute_result"
407 | }
408 | ],
409 | "source": [
410 | "lesk(doc, 'die')"
411 | ]
412 | },
413 | {
414 | "cell_type": "code",
415 | "execution_count": 38,
416 | "id": "cordless-bankruptcy",
417 | "metadata": {},
418 | "outputs": [
419 | {
420 | "data": {
421 | "text/plain": [
422 | "'a small cube with 1 to 6 spots on the six faces; used in gambling to generate random numbers'"
423 | ]
424 | },
425 | "execution_count": 38,
426 | "metadata": {},
427 | "output_type": "execute_result"
428 | }
429 | ],
430 | "source": [
431 | "lesk(doc, 'die').definition()"
432 | ]
433 | },
434 | {
435 | "cell_type": "code",
436 | "execution_count": 39,
437 | "id": "excess-consultancy",
438 | "metadata": {},
439 | "outputs": [
440 | {
441 | "data": {
442 | "text/plain": [
443 | "\"a widely used search engine that uses text-matching techniques to find web pages that are important and relevant to a user's search\""
444 | ]
445 | },
446 | "execution_count": 39,
447 | "metadata": {},
448 | "output_type": "execute_result"
449 | }
450 | ],
451 | "source": [
452 | "lesk(nlp('I work at google.'), 'google').definition()"
453 | ]
454 | },
455 | {
456 | "cell_type": "code",
457 | "execution_count": 40,
458 | "id": "infectious-binary",
459 | "metadata": {},
460 | "outputs": [
461 | {
462 | "data": {
463 | "text/plain": [
464 | "'search the internet (for information) using the Google search engine'"
465 | ]
466 | },
467 | "execution_count": 40,
468 | "metadata": {},
469 | "output_type": "execute_result"
470 | }
471 | ],
472 | "source": [
473 | "lesk(nlp('I will google it.'), 'google').definition()"
474 | ]
475 | },
476 | {
477 | "cell_type": "code",
478 | "execution_count": null,
479 | "id": "laughing-carolina",
480 | "metadata": {},
481 | "outputs": [],
482 | "source": []
483 | }
484 | ],
485 | "metadata": {
486 | "kernelspec": {
487 | "display_name": "Python 3",
488 | "language": "python",
489 | "name": "python3"
490 | },
491 | "language_info": {
492 | "codemirror_mode": {
493 | "name": "ipython",
494 | "version": 3
495 | },
496 | "file_extension": ".py",
497 | "mimetype": "text/x-python",
498 | "name": "python",
499 | "nbconvert_exporter": "python",
500 | "pygments_lexer": "ipython3",
501 | "version": "3.7.7"
502 | }
503 | },
504 | "nbformat": 4,
505 | "nbformat_minor": 5
506 | }
507 |
--------------------------------------------------------------------------------
/topic modelling/nmf-imdb-movie-reviews.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "cells": [
3 | {
4 | "cell_type": "markdown",
5 | "id": "interior-basics",
6 | "metadata": {},
7 | "source": [
8 | "# Inferring Topics from IMDB Reviews"
9 | ]
10 | },
11 | {
12 | "cell_type": "code",
13 | "execution_count": 1,
14 | "id": "established-malta",
15 | "metadata": {},
16 | "outputs": [],
17 | "source": [
18 | "import numpy as np\n",
19 | "import os\n",
20 | "from sklearn.feature_extraction.text import TfidfVectorizer\n",
21 | "from sklearn.decomposition import NMF\n",
22 | "import pandas as pd\n",
23 | "import matplotlib.pyplot as plt"
24 | ]
25 | },
26 | {
27 | "cell_type": "markdown",
28 | "id": "political-ability",
29 | "metadata": {},
30 | "source": [
31 | "## Exploring the Dataset: [Large Movie Review Dataset](https://drive.google.com/drive/u/0/folders/1umS1MgUXyra3KVF-6FsN8krHQ31lXhlX)"
32 | ]
33 | },
34 | {
35 | "cell_type": "code",
36 | "execution_count": 2,
37 | "id": "physical-speaker",
38 | "metadata": {},
39 | "outputs": [],
40 | "source": [
41 | "ROOT = '../neuralnets/aclImdb/train/pos/'"
42 | ]
43 | },
44 | {
45 | "cell_type": "code",
46 | "execution_count": 3,
47 | "id": "solar-universe",
48 | "metadata": {},
49 | "outputs": [],
50 | "source": [
51 | "reviews = []\n",
52 | "for file in os.listdir(ROOT):\n",
53 | " path = os.path.join(ROOT, file)\n",
54 | " if os.path.isfile(path):\n",
55 | " with open(path, 'r') as fin:\n",
56 | " reviews.append(fin.read())"
57 | ]
58 | },
59 | {
60 | "cell_type": "code",
61 | "execution_count": 4,
62 | "id": "permanent-pride",
63 | "metadata": {},
64 | "outputs": [
65 | {
66 | "data": {
67 | "text/plain": [
68 | "12500"
69 | ]
70 | },
71 | "execution_count": 4,
72 | "metadata": {},
73 | "output_type": "execute_result"
74 | }
75 | ],
76 | "source": [
77 | "len(reviews)"
78 | ]
79 | },
80 | {
81 | "cell_type": "code",
82 | "execution_count": 5,
83 | "id": "similar-commander",
84 | "metadata": {},
85 | "outputs": [
86 | {
87 | "name": "stdout",
88 | "output_type": "stream",
89 | "text": [
90 | "Not wishing to give *anything* away here, I would just say this technically excellent, flawlessly acted and uplifting little flic will reward the viewer with an excellent hour and a half's entertainment: It will amuse, surprise, possibly embarrass occasionally and almost certainly tug at the heartstrings from time to time, as it approaches the inevitable, but not obvious, ending without becoming clichéd or predictable in any way. Most definitely recommended.| \n", 140 | " | 00 | \n", 141 | "000 | \n", 142 | "000s | \n", 143 | "003830 | \n", 144 | "006 | \n", 145 | "007 | \n", 146 | "0079 | \n", 147 | "0080 | \n", 148 | "0083 | \n", 149 | "0093638 | \n", 150 | "... | \n", 151 | "élan | \n", 152 | "émigré | \n", 153 | "émigrés | \n", 154 | "était | \n", 155 | "état | \n", 156 | "étc | \n", 157 | "êxtase | \n", 158 | "ís | \n", 159 | "østbye | \n", 160 | "über | \n", 161 | "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", 166 | "0.0 | \n", 167 | "0.0 | \n", 168 | "0.0 | \n", 169 | "0.0 | \n", 170 | "0.0 | \n", 171 | "0.0 | \n", 172 | "0.0 | \n", 173 | "0.0 | \n", 174 | "0.0 | \n", 175 | "0.0 | \n", 176 | "... | \n", 177 | "0.0 | \n", 178 | "0.0 | \n", 179 | "0.0 | \n", 180 | "0.0 | \n", 181 | "0.0 | \n", 182 | "0.0 | \n", 183 | "0.0 | \n", 184 | "0.0 | \n", 185 | "0.0 | \n", 186 | "0.0 | \n", 187 | "
| 1 | \n", 190 | "0.0 | \n", 191 | "0.0 | \n", 192 | "0.0 | \n", 193 | "0.0 | \n", 194 | "0.0 | \n", 195 | "0.0 | \n", 196 | "0.0 | \n", 197 | "0.0 | \n", 198 | "0.0 | \n", 199 | "0.0 | \n", 200 | "... | \n", 201 | "0.0 | \n", 202 | "0.0 | \n", 203 | "0.0 | \n", 204 | "0.0 | \n", 205 | "0.0 | \n", 206 | "0.0 | \n", 207 | "0.0 | \n", 208 | "0.0 | \n", 209 | "0.0 | \n", 210 | "0.0 | \n", 211 | "
| 2 | \n", 214 | "0.0 | \n", 215 | "0.0 | \n", 216 | "0.0 | \n", 217 | "0.0 | \n", 218 | "0.0 | \n", 219 | "0.0 | \n", 220 | "0.0 | \n", 221 | "0.0 | \n", 222 | "0.0 | \n", 223 | "0.0 | \n", 224 | "... | \n", 225 | "0.0 | \n", 226 | "0.0 | \n", 227 | "0.0 | \n", 228 | "0.0 | \n", 229 | "0.0 | \n", 230 | "0.0 | \n", 231 | "0.0 | \n", 232 | "0.0 | \n", 233 | "0.0 | \n", 234 | "0.0 | \n", 235 | "
| 3 | \n", 238 | "0.0 | \n", 239 | "0.0 | \n", 240 | "0.0 | \n", 241 | "0.0 | \n", 242 | "0.0 | \n", 243 | "0.0 | \n", 244 | "0.0 | \n", 245 | "0.0 | \n", 246 | "0.0 | \n", 247 | "0.0 | \n", 248 | "... | \n", 249 | "0.0 | \n", 250 | "0.0 | \n", 251 | "0.0 | \n", 252 | "0.0 | \n", 253 | "0.0 | \n", 254 | "0.0 | \n", 255 | "0.0 | \n", 256 | "0.0 | \n", 257 | "0.0 | \n", 258 | "0.0 | \n", 259 | "
| 4 | \n", 262 | "0.0 | \n", 263 | "0.0 | \n", 264 | "0.0 | \n", 265 | "0.0 | \n", 266 | "0.0 | \n", 267 | "0.0 | \n", 268 | "0.0 | \n", 269 | "0.0 | \n", 270 | "0.0 | \n", 271 | "0.0 | \n", 272 | "... | \n", 273 | "0.0 | \n", 274 | "0.0 | \n", 275 | "0.0 | \n", 276 | "0.0 | \n", 277 | "0.0 | \n", 278 | "0.0 | \n", 279 | "0.0 | \n", 280 | "0.0 | \n", 281 | "0.0 | \n", 282 | "0.0 | \n", 283 | "
| ... | \n", 286 | "... | \n", 287 | "... | \n", 288 | "... | \n", 289 | "... | \n", 290 | "... | \n", 291 | "... | \n", 292 | "... | \n", 293 | "... | \n", 294 | "... | \n", 295 | "... | \n", 296 | "... | \n", 297 | "... | \n", 298 | "... | \n", 299 | "... | \n", 300 | "... | \n", 301 | "... | \n", 302 | "... | \n", 303 | "... | \n", 304 | "... | \n", 305 | "... | \n", 306 | "... | \n", 307 | "
| 12495 | \n", 310 | "0.0 | \n", 311 | "0.0 | \n", 312 | "0.0 | \n", 313 | "0.0 | \n", 314 | "0.0 | \n", 315 | "0.0 | \n", 316 | "0.0 | \n", 317 | "0.0 | \n", 318 | "0.0 | \n", 319 | "0.0 | \n", 320 | "... | \n", 321 | "0.0 | \n", 322 | "0.0 | \n", 323 | "0.0 | \n", 324 | "0.0 | \n", 325 | "0.0 | \n", 326 | "0.0 | \n", 327 | "0.0 | \n", 328 | "0.0 | \n", 329 | "0.0 | \n", 330 | "0.0 | \n", 331 | "
| 12496 | \n", 334 | "0.0 | \n", 335 | "0.0 | \n", 336 | "0.0 | \n", 337 | "0.0 | \n", 338 | "0.0 | \n", 339 | "0.0 | \n", 340 | "0.0 | \n", 341 | "0.0 | \n", 342 | "0.0 | \n", 343 | "0.0 | \n", 344 | "... | \n", 345 | "0.0 | \n", 346 | "0.0 | \n", 347 | "0.0 | \n", 348 | "0.0 | \n", 349 | "0.0 | \n", 350 | "0.0 | \n", 351 | "0.0 | \n", 352 | "0.0 | \n", 353 | "0.0 | \n", 354 | "0.0 | \n", 355 | "
| 12497 | \n", 358 | "0.0 | \n", 359 | "0.0 | \n", 360 | "0.0 | \n", 361 | "0.0 | \n", 362 | "0.0 | \n", 363 | "0.0 | \n", 364 | "0.0 | \n", 365 | "0.0 | \n", 366 | "0.0 | \n", 367 | "0.0 | \n", 368 | "... | \n", 369 | "0.0 | \n", 370 | "0.0 | \n", 371 | "0.0 | \n", 372 | "0.0 | \n", 373 | "0.0 | \n", 374 | "0.0 | \n", 375 | "0.0 | \n", 376 | "0.0 | \n", 377 | "0.0 | \n", 378 | "0.0 | \n", 379 | "
| 12498 | \n", 382 | "0.0 | \n", 383 | "0.0 | \n", 384 | "0.0 | \n", 385 | "0.0 | \n", 386 | "0.0 | \n", 387 | "0.0 | \n", 388 | "0.0 | \n", 389 | "0.0 | \n", 390 | "0.0 | \n", 391 | "0.0 | \n", 392 | "... | \n", 393 | "0.0 | \n", 394 | "0.0 | \n", 395 | "0.0 | \n", 396 | "0.0 | \n", 397 | "0.0 | \n", 398 | "0.0 | \n", 399 | "0.0 | \n", 400 | "0.0 | \n", 401 | "0.0 | \n", 402 | "0.0 | \n", 403 | "
| 12499 | \n", 406 | "0.0 | \n", 407 | "0.0 | \n", 408 | "0.0 | \n", 409 | "0.0 | \n", 410 | "0.0 | \n", 411 | "0.0 | \n", 412 | "0.0 | \n", 413 | "0.0 | \n", 414 | "0.0 | \n", 415 | "0.0 | \n", 416 | "... | \n", 417 | "0.0 | \n", 418 | "0.0 | \n", 419 | "0.0 | \n", 420 | "0.0 | \n", 421 | "0.0 | \n", 422 | "0.0 | \n", 423 | "0.0 | \n", 424 | "0.0 | \n", 425 | "0.0 | \n", 426 | "0.0 | \n", 427 | "
12500 rows × 55428 columns
\n", 431 | "| \n", 534 | " | Word 1 | \n", 535 | "Word 2 | \n", 536 | "Word 3 | \n", 537 | "Word 4 | \n", 538 | "Word 5 | \n", 539 | "Word 6 | \n", 540 | "Word 7 | \n", 541 | "Word 8 | \n", 542 | "Word 9 | \n", 543 | "Word 10 | \n", 544 | "
|---|---|---|---|---|---|---|---|---|---|---|
| Topic 1 | \n", 549 | "br | \n", 550 | "10 | \n", 551 | "ll | \n", 552 | "spoilers | \n", 553 | "end | \n", 554 | "simply | \n", 555 | "yes | \n", 556 | "spoiler | \n", 557 | "quite | \n", 558 | "just | \n", 559 | "
| Topic 2 | \n", 562 | "movie | \n", 563 | "movies | \n", 564 | "watch | \n", 565 | "recommend | \n", 566 | "10 | \n", 567 | "seen | \n", 568 | "saw | \n", 569 | "best | \n", 570 | "actors | \n", 571 | "definitely | \n", 572 | "
| Topic 3 | \n", 575 | "film | \n", 576 | "films | \n", 577 | "director | \n", 578 | "characters | \n", 579 | "seen | \n", 580 | "cinema | \n", 581 | "festival | \n", 582 | "work | \n", 583 | "scenes | \n", 584 | "art | \n", 585 | "
| Topic 4 | \n", 588 | "series | \n", 589 | "episode | \n", 590 | "episodes | \n", 591 | "season | \n", 592 | "tv | \n", 593 | "characters | \n", 594 | "trek | \n", 595 | "seasons | \n", 596 | "shows | \n", 597 | "television | \n", 598 | "
| Topic 5 | \n", 601 | "man | \n", 602 | "role | \n", 603 | "character | \n", 604 | "performance | \n", 605 | "best | \n", 606 | "plays | \n", 607 | "john | \n", 608 | "played | \n", 609 | "does | \n", 610 | "actor | \n", 611 | "
| Topic 6 | \n", 614 | "good | \n", 615 | "pretty | \n", 616 | "story | \n", 617 | "bad | \n", 618 | "acting | \n", 619 | "really | \n", 620 | "job | \n", 621 | "liked | \n", 622 | "nice | \n", 623 | "little | \n", 624 | "
| Topic 7 | \n", 627 | "war | \n", 628 | "world | \n", 629 | "documentary | \n", 630 | "people | \n", 631 | "american | \n", 632 | "history | \n", 633 | "soldiers | \n", 634 | "men | \n", 635 | "women | \n", 636 | "hitler | \n", 637 | "
| Topic 8 | \n", 640 | "funny | \n", 641 | "comedy | \n", 642 | "laugh | \n", 643 | "hilarious | \n", 644 | "eddie | \n", 645 | "fun | \n", 646 | "jokes | \n", 647 | "humor | \n", 648 | "funniest | \n", 649 | "murphy | \n", 650 | "
| Topic 9 | \n", 653 | "like | \n", 654 | "think | \n", 655 | "really | \n", 656 | "just | \n", 657 | "don | \n", 658 | "people | \n", 659 | "know | \n", 660 | "say | \n", 661 | "didn | \n", 662 | "lot | \n", 663 | "
| Topic 10 | \n", 666 | "time | \n", 667 | "years | \n", 668 | "saw | \n", 669 | "seen | \n", 670 | "dvd | \n", 671 | "old | \n", 672 | "remember | \n", 673 | "ve | \n", 674 | "music | \n", 675 | "disney | \n", 676 | "
| Topic 11 | \n", 679 | "life | \n", 680 | "story | \n", 681 | "love | \n", 682 | "family | \n", 683 | "real | \n", 684 | "characters | \n", 685 | "people | \n", 686 | "young | \n", 687 | "beautiful | \n", 688 | "true | \n", 689 | "
| Topic 12 | \n", 692 | "book | \n", 693 | "jane | \n", 694 | "version | \n", 695 | "read | \n", 696 | "eyre | \n", 697 | "novel | \n", 698 | "rochester | \n", 699 | "dalton | \n", 700 | "tarzan | \n", 701 | "emma | \n", 702 | "
| Topic 13 | \n", 705 | "horror | \n", 706 | "house | \n", 707 | "creepy | \n", 708 | "scary | \n", 709 | "gore | \n", 710 | "films | \n", 711 | "halloween | \n", 712 | "budget | \n", 713 | "fans | \n", 714 | "effects | \n", 715 | "
| Topic 14 | \n", 718 | "great | \n", 719 | "acting | \n", 720 | "really | \n", 721 | "actors | \n", 722 | "cast | \n", 723 | "job | \n", 724 | "best | \n", 725 | "music | \n", 726 | "wonderful | \n", 727 | "just | \n", 728 | "
| Topic 15 | \n", 731 | "action | \n", 732 | "jackie | \n", 733 | "chan | \n", 734 | "scenes | \n", 735 | "fu | \n", 736 | "kung | \n", 737 | "fight | \n", 738 | "martial | \n", 739 | "bourne | \n", 740 | "story | \n", 741 | "
| \n", 846 | " | Topic 1 | \n", 847 | "Topic 2 | \n", 848 | "Topic 3 | \n", 849 | "Topic 4 | \n", 850 | "Topic 5 | \n", 851 | "Topic 6 | \n", 852 | "Topic 7 | \n", 853 | "Topic 8 | \n", 854 | "Topic 9 | \n", 855 | "Topic 10 | \n", 856 | "Topic 11 | \n", 857 | "Topic 12 | \n", 858 | "Topic 13 | \n", 859 | "Topic 14 | \n", 860 | "Topic 15 | \n", 861 | "max_topic | \n", 862 | "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | \n", 867 | "0.028314 | \n", 868 | "0.000000 | \n", 869 | "0.022122 | \n", 870 | "0.001480 | \n", 871 | "0.023043 | \n", 872 | "0.002044 | \n", 873 | "0.030939 | \n", 874 | "0.000000 | \n", 875 | "0.006389 | \n", 876 | "0.000000 | \n", 877 | "0.000774 | \n", 878 | "0.007251 | \n", 879 | "0.000000 | \n", 880 | "0.003574 | \n", 881 | "0.000000 | \n", 882 | "War | \n", 883 | "
| 16 | \n", 886 | "0.000251 | \n", 887 | "0.000000 | \n", 888 | "0.001575 | \n", 889 | "0.000000 | \n", 890 | "0.029132 | \n", 891 | "0.002257 | \n", 892 | "0.000000 | \n", 893 | "0.033108 | \n", 894 | "0.016283 | \n", 895 | "0.000000 | \n", 896 | "0.012337 | \n", 897 | "0.000000 | \n", 898 | "0.003595 | \n", 899 | "0.011944 | \n", 900 | "0.010159 | \n", 901 | "Comedy | \n", 902 | "
| 18 | \n", 905 | "0.029574 | \n", 906 | "0.000000 | \n", 907 | "0.019010 | \n", 908 | "0.001797 | \n", 909 | "0.016906 | \n", 910 | "0.008574 | \n", 911 | "0.000129 | \n", 912 | "0.038010 | \n", 913 | "0.005558 | \n", 914 | "0.006250 | \n", 915 | "0.036652 | \n", 916 | "0.000000 | \n", 917 | "0.000000 | \n", 918 | "0.000000 | \n", 919 | "0.000000 | \n", 920 | "Comedy | \n", 921 | "
| 26 | \n", 924 | "0.015179 | \n", 925 | "0.000349 | \n", 926 | "0.000000 | \n", 927 | "0.000000 | \n", 928 | "0.015907 | \n", 929 | "0.012349 | \n", 930 | "0.000000 | \n", 931 | "0.034328 | \n", 932 | "0.015722 | \n", 933 | "0.008809 | \n", 934 | "0.004318 | \n", 935 | "0.000000 | \n", 936 | "0.000000 | \n", 937 | "0.001958 | \n", 938 | "0.000922 | \n", 939 | "Comedy | \n", 940 | "
| 27 | \n", 943 | "0.031523 | \n", 944 | "0.008099 | \n", 945 | "0.000171 | \n", 946 | "0.003151 | \n", 947 | "0.009975 | \n", 948 | "0.001411 | \n", 949 | "0.035158 | \n", 950 | "0.042588 | \n", 951 | "0.000000 | \n", 952 | "0.000000 | \n", 953 | "0.001425 | \n", 954 | "0.002624 | \n", 955 | "0.000000 | \n", 956 | "0.003865 | \n", 957 | "0.002781 | \n", 958 | "Comedy | \n", 959 | "
| 29 | \n", 962 | "0.000000 | \n", 963 | "0.000614 | \n", 964 | "0.000000 | \n", 965 | "0.000000 | \n", 966 | "0.000000 | \n", 967 | "0.014862 | \n", 968 | "0.000000 | \n", 969 | "0.014987 | \n", 970 | "0.010941 | \n", 971 | "0.000000 | \n", 972 | "0.000000 | \n", 973 | "0.001534 | \n", 974 | "0.066263 | \n", 975 | "0.000000 | \n", 976 | "0.036239 | \n", 977 | "Horror | \n", 978 | "
| 30 | \n", 981 | "0.023404 | \n", 982 | "0.012107 | \n", 983 | "0.016814 | \n", 984 | "0.000000 | \n", 985 | "0.008135 | \n", 986 | "0.009620 | \n", 987 | "0.001377 | \n", 988 | "0.040382 | \n", 989 | "0.000809 | \n", 990 | "0.004582 | \n", 991 | "0.004803 | \n", 992 | "0.001186 | \n", 993 | "0.014194 | \n", 994 | "0.000000 | \n", 995 | "0.000000 | \n", 996 | "Comedy | \n", 997 | "
| 31 | \n", 1000 | "0.012324 | \n", 1001 | "0.003554 | \n", 1002 | "0.028753 | \n", 1003 | "0.000000 | \n", 1004 | "0.017125 | \n", 1005 | "0.003483 | \n", 1006 | "0.006804 | \n", 1007 | "0.000000 | \n", 1008 | "0.003702 | \n", 1009 | "0.000000 | \n", 1010 | "0.006449 | \n", 1011 | "0.000833 | \n", 1012 | "0.034161 | \n", 1013 | "0.005682 | \n", 1014 | "0.000000 | \n", 1015 | "Horror | \n", 1016 | "
| 34 | \n", 1019 | "0.000000 | \n", 1020 | "0.016503 | \n", 1021 | "0.000000 | \n", 1022 | "0.000000 | \n", 1023 | "0.013825 | \n", 1024 | "0.000000 | \n", 1025 | "0.000000 | \n", 1026 | "0.038567 | \n", 1027 | "0.004479 | \n", 1028 | "0.021462 | \n", 1029 | "0.000000 | \n", 1030 | "0.000000 | \n", 1031 | "0.000000 | \n", 1032 | "0.010132 | \n", 1033 | "0.000000 | \n", 1034 | "Comedy | \n", 1035 | "
| 58 | \n", 1038 | "0.000228 | \n", 1039 | "0.046686 | \n", 1040 | "0.000000 | \n", 1041 | "0.000000 | \n", 1042 | "0.000100 | \n", 1043 | "0.000000 | \n", 1044 | "0.004866 | \n", 1045 | "0.000000 | \n", 1046 | "0.001639 | \n", 1047 | "0.013741 | \n", 1048 | "0.037063 | \n", 1049 | "0.069237 | \n", 1050 | "0.000000 | \n", 1051 | "0.012097 | \n", 1052 | "0.000000 | \n", 1053 | "Book Adaptation | \n", 1054 | "
| \n", 113 | " | text | \n", 114 | "label | \n", 115 | "
|---|---|---|
| 4966 | \n", 120 | "Humm, an Italian movie starred by David hasselhoff and Linda Blair, I wasn´t expecting very much, to be honest and in fact, I took even less than I was expecting. It doesn´t mean this movie is the... | \n", 121 | "0 | \n", 122 | "
| 24885 | \n", 125 | "Not only was this movie better than all the final season of H:LOTS. But it was better than any movie made for TV I have ever seen!<br /><br />Looking at the \"Top 250\" I see that only one small scr... | \n", 126 | "1 | \n", 127 | "
| 2310 | \n", 130 | "This is a well-worn story about a man who marries to escape the hangman's noose, then sets about \"taming\" his reluctant bride. It manages to be sexist and racist at exactly the same time. We never... | \n", 131 | "0 | \n", 132 | "
| 13648 | \n", 135 | "Being from a small town in Illinois myself, I can instantly relate to this movie. Considering the era it was made in, the townsfolk look uncomfortably like a lot of people I grew up with. Yes the ... | \n", 136 | "1 | \n", 137 | "
| 4021 | \n", 140 | "(David H. Steinberg)'s script seemed initially having some real smart points that could've made good romantic comedy, BUT BUT BUT, oh dear ! What did ever happen in the way ???!!!! <br /><br />I'l... | \n", 141 | "0 | \n", 142 | "