Gist 6437893f183d99e863d835425ffa46f8

100%

Gist 6437893f183d99e863d835425ffa46f8

✓ Published0🌍 Public

Last edited Dec 29, 2021

Created on Dec 29, 2021

This example visualizes the distribution of tokenized caption text from a dataset of images, showing how frequently each word appears after cleaning. The visualization displays the processed terms as a bar chart or word cloud, with the data derived from the `Caption` field of the input dataframe. The preprocessing pipeline loads the `en_core_web_lg` spaCy model to tokenize each caption, removes English stop words and non-alphanumeric characters, and converts all terms to lowercase. The code relies on the `spacy` library for linguistic analysis and standard Python regex operations via the `re` module to filter tokens, while the `stopwords` set comes from NLTK.

AI-generated description

Similar vizzes

Loading thumbnail…

Gist 55fc864ec9cea1107845d3ed7a3dab8b

This example demonstrates a text-cleaning pipeline for caption data, showing how raw captions are converted into tokenized, filtered lists for downstream analysis. The visualization itself is not rendered; instead, the focus is on the data preprocessing logic. The code uses `pandas` with `apply` to run natural language processing via `spaCy` (`nlp`), extracting tokens from the `Caption` column. It then applies a custom `tokens` function that removes stop words and non-alphanumeric characters using `re.match`, while preserving tokens containing "@" symbols. The result is a new `clean_caption` column, highlighting a common step in text mining workflows.

AArizonaTay

86% match

Loading thumbnail…

Gist af6ed0a95b476ea7f82b0576a93a2306

This visualization displays the 30 most common words from a dataset of cleaned captions, using a frequency distribution to show which terms appear most often. The code filters out common exclusions like "1," "2," and "3" before processing, then relies on the Natural Language Toolkit’s `FreqDist` to count word occurrences. A bar chart is generated with `matplotlib.pyplot`, where the horizontal axis lists the top words and the vertical axis shows their raw frequencies. The plot is sized at 14 by 6 inches for readability, and the resulting figure is displayed directly via `plt.show()`, with the source being an internal data frame of cleaned captions.

AArizonaTay

80% match

Loading thumbnail…

Gist fbc8e33e01b5be01bc6c1ab2d1d08cfc

The visualization displays the 30 most frequently occurring words from a set of cleaned Instagram captions, plotted as a bar chart that ranks terms by raw count. It shows a sharp drop-off in frequency after the top few words, highlighting the long-tail distribution common in text data. The chart is generated using Python’s matplotlib, with the caption data loaded into a pandas DataFrame and tokenized via the Natural Language Toolkit (nltk). Frequencies are computed with `nltk.FreqDist`, and the top 30 entries are selected for plotting, with a filter excluding the characters ‘1’, ‘2’, and ‘3’ from the hashtag tokens. The figure is sized at 14 by 6 inches for readability.

AArizonaTay

73% match

Loading thumbnail…

Gist 6499e03ffdfc7479408da70f20af3625

This visualization maps the semantic relationships between words extracted from a text corpus. It shows a network of nodes and edges, where connected words cluster together based on their contextual similarity. The layout uses a force-directed graph, likely powered by d3.forceSimulation, to position nodes and links. The code loads a spaCy NLP model (`en_core_web_lg`) to compute word vectors, and filters out stop words using NLTK’s stopwords list before processing the raw text.

AArizonaTay

70% match

Loading thumbnail…

Gist 751982c1e21147b124a9b6d5fde96a4e

The visualization examines sponsored content in a social media dataset by processing raw captions through a custom pipeline. It uses Python’s `re` module to strip emojis and punctuation, then applies spaCy’s named entity recognition to extract organizations and products into a "Sponsor" list, while also capturing tags via string matching. The code builds a DataFrame with `pandas`, adding a binary "Sponsored" column based on whether either field is non-empty. It highlights the detection of promotional mentions by combining entity-based and rule-based tagging, ultimately displaying cleaned captions alongside the derived sponsorship metadata.

AArizonaTay

70% match

Loading thumbnail…

Gist da5f7a5f8cf01b0874d92349b33ec806

This visualization uses a Latent Dirichlet Allocation (LDA) topic model to classify Instagram captions into eight thematic categories, such as Giveaway, Fitness, and Love. It first shows the derived topics with their top ten keywords per topic, then assigns each caption its dominant topic and displays a random sample of the resulting annotations. The analysis relies on the Gensim library for the LDA model and coherence scoring, while Pandas DataFrames and the Dictionary and doc2bow APIs handle text preprocessing and corpus construction. A custom function maps each caption’s topic distribution to its most likely label, and the final output presents a sample of the enriched data with the assigned topic column.

AArizonaTay

69% match

Loading thumbnail…

Gist e049bb6d7696d1b2d4ff242e68fcd062

This example analyzes text data by performing topic modeling and visualization. It shows the resulting topics and their associated terms, revealing latent themes in the dataset. The code uses NLTK for tokenization and stopword removal, TextBlob for sentiment analysis, and Gensim’s LdaModel and CoherenceModel for topic extraction. Plotly’s `scatter` and `bar` traces render the interactive visualizations, with data processed from a pandas DataFrame. The rendering approach relies on Plotly’s offline mode, initiated via `pyo.init_notebook_mode()`.

AArizonaTay

69% match

Loading thumbnail…

Gist dec05c8e23491da95f80ba891c35100a

This example trains a custom named entity recognition (NER) model using spaCy to identify sponsor mentions, product names, and promo codes in social media captions. It first preprocesses a data frame of captions by stripping non-alphabetic characters, then initializes a pre-trained English model and adds custom labels. Training uses 10 epochs with minibatch compounding and dropout, iterating over hand-labeled examples that mark entity spans. After training, the model is saved to disk and reloaded to test inference on new text, demonstrating the pipeline’s ability to extract promotional entities from informal, hashtag-heavy captions.

AArizonaTay

68% match