Demo Day Page Google Classifier - Revision history

Ed at 17:47, 21 September 2020

2020-09-21T17:47:34Z

Ed at 17:34, 21 September 2020

2020-09-21T17:34:29Z

Ed at 17:19, 20 September 2020

2020-09-20T17:19:57Z

Ed at 17:12, 20 September 2020

2020-09-20T17:12:10Z

Leminh.ams at 19:41, 20 June 2018

2018-06-20T19:41:27Z

Leminh.ams at 19:36, 20 June 2018

2018-06-20T19:36:59Z

Kyranstar at 20:46, 18 May 2018

2018-05-18T20:46:58Z

Kyranstar at 20:43, 18 May 2018

2018-05-18T20:43:37Z

Kyranstar: /* Possible further steps */

2018-05-18T02:03:12Z

Possible further steps

Kyranstar at 16:58, 17 May 2018

2018-05-17T16:58:47Z

@@ Line 1: / Line 1: @@
 {{Project
-|Has project output=
+|Has project output=Tool
 |Has sponsor=McNair Center
 |Has title=Demo Day Page Google Classifier

@@ Line 1: / Line 1: @@
 {{Project
 |Has sponsor=McNair Center
 |Has title=Demo Day Page Google Classifier

@@ Line 1: / Line 1: @@
 {{Project
 |Has title=Demo Day Page Google Classifier
 |Has owner=Kyran Adams,

@@ Line 1: / Line 1: @@
-{{McNair Projects
+{{Project
 |Has title=Demo Day Page Google Classifier
 |Has owner=Kyran Adams,

@@ Line 4: / Line 4: @@
 |Has start date=2/5/2018
 |Has keywords=Accelerator, Demo Day, Google Result, Word2vec, Tensorflow
-|Has project status=Complete
+|Has project status=Subsume
 |Is dependent on=Accelerator Seed List (Data), Demo Day Page Parser
 }}

@@ Line 12: / Line 12: @@
 This is a ML project that classifies webpages as a demo day page containing a list of cohort companies, currently using scikit learn's random forest model and a bag of words approach. Currently about 80% accuracy, though this would be vastly improved with more training data. The classifier currently really overfits the training data. The classifier itself takes:
-<strong>Input features:</strong> This is calculated by web_demo_features.py in the same directory and output to a tsv file. It takes: the frequencies of each word from words.txt,  month words grouped in seasons, and phrases of the form "# startups". It also takes the number of simple links (links in the form www.abc.com or www.abc.org) and the number of those that are attached to images. It also takes the number of "strong" html tags in the body. These features can be extended by adding words to words.txt or regexes to the PATTERNS variable in web_demo_features.py. There is also unused code for generating tfidf frequencies, this might improve the classifier if we had more data. Currently it does not.
+<strong>Input features:</strong> This is calculated by web_demo_features.py in the same directory and output to a tsv file. It takes: the frequencies of each word from words.txt,  month words grouped in seasons, and phrases of the form "# startups". It also takes the number of simple links (links in the form www.abc.com or www.abc.org) and the number of those that are attached to images. It also takes the number of "strong" html tags in the body. These features can be extended by adding words to words.txt or regexes to the PATTERNS variable in web_demo_features.py. There is also unused code for generating monogram/bigram tfidf frequencies, this might improve the classifier if we had more data.
 <strong>Training data:</strong> A set of webpages hand-classified as to whether they contain a list of cohort companies. The classification is stored in classification.txt, which is a tsv equivalent of Demo Day URLS.xlsx. Keep in mind that this txt file must be utf-8 encoded. In textpad, one can convert a file to utf-8 by pressing save-as, and changing the encoding at the bottom. The HTML pages themselves are stored in DemoDayHTMLFull.
@@ Line 23: / Line 23: @@
 <strong>Usage:</strong>
-* Steps to add training data to the model: Put all of the html files to be used in DemoDayHTMLFull. Put corresponding entries into demo_day_cohort_lists.xlsx (only the columns "URL" and "Cohort" are necessary, but they must be in alphabetical order. data_reader.py will throw error otherwise), then export it to classification.txt. Convert this to utf-8 (textpad can do this, just save as -> encoding:utf-8). Then run web_demo_features.py to generate the features matrix, hand_training_features.txt. Then, run demo_day_classifier_randforest.py to generate the model, classifier.pkl.
+* Steps to add training data to the model: Put all of the html files to be used in DemoDayHTMLFull. Put corresponding entries into demo_day_cohort_lists.xlsx (only the columns "URL" and "Cohort" are necessary, but they must be in alphabetical order. data_reader.py will throw error otherwise), then export it to classification.txt. Convert this to utf-8 (textpad can do this, just save as -> encoding:utf-8). Then run:
 * Steps to run the model on google results: In the file crawl_and_classify.py, set the variables to whatever is wanted. Then, run this command:

@@ Line 10: / Line 10: @@
 ==Project==
-This is a ML project that classifies webpages as a demo day page containing a list of cohort companies, currently using scikit learn's random forest model and a bag of words approach. Currently about 80% accuracy, though this would be vastly improved with more training data. The classifier itself takes:
+This is a ML project that classifies webpages as a demo day page containing a list of cohort companies, currently using scikit learn's random forest model and a bag of words approach. Currently about 80% accuracy, though this would be vastly improved with more training data. The classifier currently really overfits the training data. The classifier itself takes:
-<strong>Features:</strong> The frequencies of each word from words.txt in the webpage. This is calculated by web_demo_features.py in the same directory. It also takes the frequencies of years from 1900-2099, month words grouped in seasons, and phrases of the form "# startups". It also takes the number of simple links (links in the form www.abc.com or www.abc.org) and the number of those that are attached to images. It also takes the number of "strong" html tags in the body. These features can be extended by adding words to words.txt or regexes to PATTERNS in web_demo_features.py.
+<strong>Input features:</strong> This is calculated by web_demo_features.py in the same directory and output to a tsv file. It takes: the frequencies of each word from words.txt,  month words grouped in seasons, and phrases of the form "# startups". It also takes the number of simple links (links in the form www.abc.com or www.abc.org) and the number of those that are attached to images. It also takes the number of "strong" html tags in the body. These features can be extended by adding words to words.txt or regexes to the PATTERNS variable in web_demo_features.py. There is also unused code for generating tfidf frequencies, this might improve the classifier if we had more data. Currently it does not.
-<strong>Training classifications:</strong> A set of webpages hand-classified as to whether they contain a list of cohort companies. This is stored in classification.txt, which is a tsv equivalent of Demo Day URLS.xlsx. Keep in mind that this txt file must be utf-8 encoded. In textpad, one can convert a file to utf-8 by pressing save-as, and changing the encoding at the bottom.
+<strong>Training data:</strong> A set of webpages hand-classified as to whether they contain a list of cohort companies. The classification is stored in classification.txt, which is a tsv equivalent of Demo Day URLS.xlsx. Keep in mind that this txt file must be utf-8 encoded. In textpad, one can convert a file to utf-8 by pressing save-as, and changing the encoding at the bottom. The HTML pages themselves are stored in DemoDayHTMLFull.
 A demo day page is an advertisement page for a "demo day," which is a day that cohorts graduating from accelerators can pitch their ideas to investors. These demo days give us a good idea of when these cohorts graduated from their accelerator.
@@ Line 23: / Line 23: @@
 <strong>Usage:</strong>
-* Steps to train the model: Put all of the html files to be used in DemoDayHTMLFull. Put corresponding entries into demo_day_cohort_lists.xlsx, then export it to classification.txt. Convert this to utf-8. Then run web_demo_features.py to generate the features matrix, training_features.txt. Then, run demo_day_classifier_randforest.py to generate the model, classifier.pkl.
+* Steps to add training data to the model: Put all of the html files to be used in DemoDayHTMLFull. Put corresponding entries into demo_day_cohort_lists.xlsx (only the columns "URL" and "Cohort" are necessary, but they must be in alphabetical order. data_reader.py will throw error otherwise), then export it to classification.txt. Convert this to utf-8 (textpad can do this, just save as -> encoding:utf-8). Then run web_demo_features.py to generate the features matrix, hand_training_features.txt. Then, run demo_day_classifier_randforest.py to generate the model, classifier.pkl.
 * Steps to run the model on google results: In the file crawl_and_classify.py, set the variables to whatever is wanted. Then, run this command:
    python3 crawl_and_classify.py
-It will download all of the html files into the directory CrawledHTMLPages, and then it will generate a matrix of features, CrawledHTMLPages\features.txt. It will then run the trained model saved in classifier.pkl to predict whether these pages are demo day pages, and then it will save the results to CrawledHTMLPages\predicted.txt. The HTML pages are then moved into CrawledHTMlPages/demoday/ or CrawledHtmlPages/non_demoday based on their prediction.
+It will download all of the html files into the directory CrawledHTMLPages, and then it will generate a matrix of features, CrawledHTMLPages\features.txt. It will then run the trained model saved in classifier.pkl to predict whether these pages are demo day pages, and then it will save the results to CrawledHTMLPages\predicted.txt. The HTML pages are then moved into CrawledHTMlPages/positive/ or CrawledHtmlPages/negative/ based on their prediction. If you want to run the classifier on html files already downloaded, the function classify_dir in crawl_and_classify.py will do this.
 ==Files and Directories==
 * CrawledHTMLPages
-** Contains the results from crawl_and_classify.py, stored in positive and negative folders based on how the html files are classified.
+** Contains the classified html file results from crawl_and_classify.py, stored in positive and negative folders based on how they are classified.
 * DemoDayHTMLFull
-** Contains the training data for the classifier. demo_day_cohort_lists.xlsx is the classification (converted to classification.txt before use), and the html files are used for generating the features matrix.
+** Contains the training data for the classifier. demo_day_cohort_lists.xlsx is the classification (same as classification.txt, which is actually used by the program, but the excel file has hyperlinks), and the html files are used for generating the features matrix.
 * demo_day_classifier_randforest.py
-** The classifier itself. A pkl'ed version of the classifier should be saved in classifier.pkl.
+** The classifier itself. A pickled version of the classifier should be saved in classifier.pkl.
 * web_demo_features.py
-** Generates the features matrix from a directory of html files to be used in the classifier.
+** Generates the features matrix from a directory of html files to be used in the classifier. See input features.
 * words.txt
 ** The words for the features. The frequency of each word is used as a feature (maybe change this to tfidf?)
@@ Line 49: / Line 49: @@
 ** Generates a little image to show how the number of features differs between demoday and non-demoday pages.
 * delete_duplicate_classified.py
-** Looks through CrawledHTMLPages/positive and CrawledHTMLPages/negative and deletes all the duplicate files.
+** Looks through CrawledHTMLPages/positive and CrawledHTMLPages/negative and deletes all the duplicate files. Run this after the crawler runs, because there are lots of duplicates from google results.
 * classify_all_accelerator.py
-** Taking the TSV files MasterAcceleratorList.tsv and SplitAcceleratorList.tsv, it googles and classifies all accelerators from MasterAcceleratorList that are not already in SplitAcceleratorList.
+** Taking the TSV files MasterAcceleratorList.tsv and SplitAcceleratorList.tsv, it googles and classifies all accelerators from MasterAcceleratorList that are not already in SplitAcceleratorList. These tsv files were exported from the Master Variable List on google sheets.
 ==Possible further steps==
-Changed from Bag-Of-Words model to a more powerful neural network, perhaps an RNN. This would likely need even more data, though. The best way to collect more data would probably be to automate/make easier the process of data collection, and just have a few people collect a few thousand points of data. This would likely improve accuracy a lot, and allow for more sophisticated classification methods.
+Change from Bag-Of-Words model to a more powerful neural network, perhaps an RNN, or use full tfidf monogram/bigram frequencies. This would need even more data, though. The best way to collect more data would probably be to automate/make easier the process of data collection, and just have a few people collect a few thousand points of data, or use mechanical turk. This would likely improve accuracy a lot, and allow for more sophisticated classification methods.

← Older revision		Revision as of 02:03, 18 May 2018
Line 56:		Line 56:
	==Possible further steps==		==Possible further steps==

−	Changed from Bag-Of-Words model to a more powerful neural network, perhaps an RNN. This would likely need even more data, though.	+	Changed from Bag-Of-Words model to a more powerful neural network, perhaps an RNN. This would likely need even more data, though. The best way to collect more data would probably be to automate/make easier the process of data collection, and just have a few people collect a few thousand points of data. This would likely improve accuracy a lot, and allow for more sophisticated classification methods.