From 8df256d749d598cec3ca260e62d6b4836039fa6f Mon Sep 17 00:00:00 2001
From: hudssntao <145732608+hudssntao@users.noreply.github.com>
Date: Fri, 27 Oct 2023 00:06:59 -0400
Subject: [PATCH 01/24] Add files via upload

---
 src/prompt_systematic_review/pipeline.py | 38 ++++++++++++++++++++++++
 1 file changed, 38 insertions(+)
 create mode 100644 src/prompt_systematic_review/pipeline.py

diff --git a/src/prompt_systematic_review/pipeline.py b/src/prompt_systematic_review/pipeline.py
new file mode 100644
index 0000000..1820ae9
--- /dev/null
+++ b/src/prompt_systematic_review/pipeline.py
@@ -0,0 +1,38 @@
+from datasets import load_dataset, concatenate_datasets
+
+"""
+Gets Huggingface dataset
+dataset_name: The name of the dataset on Huggingface
+user_name: The name under which the dataset has been created
+Returns a Dataset object
+"""
+def get(dataset_name, user_name):
+    return load_dataset(user_name + "/" + dataset_name)
+
+"""
+Replaces entire database in Huggingface
+dataset_name: The name of the dataset on Huggingface
+new_dataset: A Dataset object containing the new dataset
+"""
+def push(dataset_name, new_dataset):
+    new_dataset.push_to_hub(dataset_name)
+
+"""
+Appends to current dataset in Huggingface (experimental)
+user_name: The name under which the dataset has been created
+dataset_name: The name of the dataset on Huggingface
+new_dataset: A Dataset object containing the new dataset
+"""
+def append(user_name, dataset_name, new_dataset):
+    
+    #Try-except for empty dataset case
+    try:
+        #Assuming split 'train' as it seems to be the default split
+        dataset = load_dataset(user_name + "/" + dataset_name, split="train")
+        appended_dataset = concatenate_datasets([dataset,new_dataset])
+        appended_dataset.push_to_hub(dataset_name)
+    except:
+        push(dataset_name, new_dataset)
+
+
+

From 06cc8d563ef9e3c592ed900fb569a91d225fec15 Mon Sep 17 00:00:00 2001
From: hudssntao <145732608+hudssntao@users.noreply.github.com>
Date: Fri, 27 Oct 2023 00:08:10 -0400
Subject: [PATCH 02/24] Add files via upload

---
 tests/pipeline_tests.py | 47 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 47 insertions(+)
 create mode 100644 tests/pipeline_tests.py

diff --git a/tests/pipeline_tests.py b/tests/pipeline_tests.py
new file mode 100644
index 0000000..dbd0b55
--- /dev/null
+++ b/tests/pipeline_tests.py
@@ -0,0 +1,47 @@
+from datasets import Dataset
+import time
+from pipeline import push, append, get
+
+def testingPushAndGet(dataset_name, user_name):
+    sample_data = {
+        "column1": ["value1", "value2", "value3"],
+        "column2": ["valueA", "valueB", "valueC"],
+    }
+
+    sample_dataset = Dataset.from_dict(sample_data)
+
+    push(dataset_name, sample_dataset)
+    assert(getRows(dataset_name, user_name) == 3)
+
+#Append seems to work on Hugging face but I'm having trouble with the Database API, will leave out this test for now.
+# def testingAppend(dataset_name, user_name):
+#     sample_data = {
+#         "column1": ["value4", "value5"],
+#         "column2": ["valueD", "valueE"],
+#     }
+
+#     sample_dataset = Dataset.from_dict(sample_data)
+
+#     append(user_name, dataset_name, sample_dataset)
+    
+#     assert(getRows(dataset_name, user_name) == 5)
+
+
+#Returns the number of rows in the dataset
+def getRows(dataset_name, user_name):
+    my_dataset = get(dataset_name, user_name)['train']
+
+    return my_dataset.num_rows
+
+if (__name__ == "__main__"):
+
+    USERNAME = "hudssntao"
+    DATASET_NAME = "test2"
+
+    testingPushAndGet(DATASET_NAME, USERNAME)
+
+    # testingAppend(DATASET_NAME, USERNAME)
+
+
+
+

From d807248ff09fa0066856916d50ae203a9ffefd4e Mon Sep 17 00:00:00 2001
From: Michael Ilie <mcilieg@gmail.com>
Date: Fri, 27 Oct 2023 16:18:38 -0400
Subject: [PATCH 03/24] added pipeline and tests

---
 src/prompt_systematic_review/pipeline.py | 52 +++++++++---------------
 tests/test_pipeline.py                   |  6 +++
 2 files changed, 25 insertions(+), 33 deletions(-)
 create mode 100644 tests/test_pipeline.py

diff --git a/src/prompt_systematic_review/pipeline.py b/src/prompt_systematic_review/pipeline.py
index 1820ae9..bb5f2f6 100644
--- a/src/prompt_systematic_review/pipeline.py
+++ b/src/prompt_systematic_review/pipeline.py
@@ -1,38 +1,24 @@
-from datasets import load_dataset, concatenate_datasets
+from datasets import load_dataset, Dataset
+import os
 
-"""
-Gets Huggingface dataset
-dataset_name: The name of the dataset on Huggingface
-user_name: The name under which the dataset has been created
-Returns a Dataset object
-"""
-def get(dataset_name, user_name):
-    return load_dataset(user_name + "/" + dataset_name)
 
-"""
-Replaces entire database in Huggingface
-dataset_name: The name of the dataset on Huggingface
-new_dataset: A Dataset object containing the new dataset
-"""
-def push(dataset_name, new_dataset):
-    new_dataset.push_to_hub(dataset_name)
-
-"""
-Appends to current dataset in Huggingface (experimental)
-user_name: The name under which the dataset has been created
-dataset_name: The name of the dataset on Huggingface
-new_dataset: A Dataset object containing the new dataset
-"""
-def append(user_name, dataset_name, new_dataset):
+def is_authenticated_with_huggingface():
+    """
+    Check if the user is authenticated with huggingface-cli.
+    Returns:
+    - bool: True if authenticated, False otherwise.
+    """
+    token_path = os.path.join(os.path.expanduser("~"), ".huggingface", "token")
+    # Check if the token file exists
+    if not os.path.exists(token_path):
+        return False
+    # Check if the token file has content (i.e., the token)
+    with open(token_path, 'r') as f:
+        token = f.read().strip()
+        if not token:
+            return False
     
-    #Try-except for empty dataset case
-    try:
-        #Assuming split 'train' as it seems to be the default split
-        dataset = load_dataset(user_name + "/" + dataset_name, split="train")
-        appended_dataset = concatenate_datasets([dataset,new_dataset])
-        appended_dataset.push_to_hub(dataset_name)
-    except:
-        push(dataset_name, new_dataset)
-
+    return True
 
 
+#make sure
diff --git a/tests/test_pipeline.py b/tests/test_pipeline.py
new file mode 100644
index 0000000..8b42dde
--- /dev/null
+++ b/tests/test_pipeline.py
@@ -0,0 +1,6 @@
+# test_pipeline.py
+import pytest
+from prompt_systematic_review.pipeline import is_authenticated
+
+def test_is_authenticated():
+    assert is_authenticated() == False
\ No newline at end of file

From 7493c163f76e59e094296ff4467c6e8321137231 Mon Sep 17 00:00:00 2001
From: Michael Ilie <mcilieg@gmail.com>
Date: Fri, 27 Oct 2023 16:20:40 -0400
Subject: [PATCH 04/24] updated cfg and deps

---
 requirements.txt | 2 ++
 setup.cfg        | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/requirements.txt b/requirements.txt
index f6687e1..632d313 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -2,4 +2,6 @@ numpy
 pandas
 requests
 matplotlib
+datasets
+huggingface_hub
 -e .
\ No newline at end of file
diff --git a/setup.cfg b/setup.cfg
index 27c3bd9..e9b1a37 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -30,6 +30,8 @@ install_requires =
     pandas
     requests
     matplotlib
+    datasets
+    huggingface_hub
 
 [options.packages.find]
 where=src

From 9b83b124ec9c22628464ea0c27f9c83e59867571 Mon Sep 17 00:00:00 2001
From: Michael Ilie <mcilieg@gmail.com>
Date: Fri, 27 Oct 2023 16:24:56 -0400
Subject: [PATCH 05/24] my tests are cursed

---
 src/prompt_systematic_review/pipeline.py | 5 ++++-
 tests/test_pipeline.py                   | 5 ++++-
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/src/prompt_systematic_review/pipeline.py b/src/prompt_systematic_review/pipeline.py
index bb5f2f6..d8b844c 100644
--- a/src/prompt_systematic_review/pipeline.py
+++ b/src/prompt_systematic_review/pipeline.py
@@ -2,7 +2,7 @@
 import os
 
 
-def is_authenticated_with_huggingface():
+def is_authenticated():
     """
     Check if the user is authenticated with huggingface-cli.
     Returns:
@@ -22,3 +22,6 @@ def is_authenticated_with_huggingface():
 
 
 #make sure
+
+def dummyfunc():
+    return True
\ No newline at end of file
diff --git a/tests/test_pipeline.py b/tests/test_pipeline.py
index 8b42dde..9fb9a64 100644
--- a/tests/test_pipeline.py
+++ b/tests/test_pipeline.py
@@ -3,4 +3,7 @@
 from prompt_systematic_review.pipeline import is_authenticated
 
 def test_is_authenticated():
-    assert is_authenticated() == False
\ No newline at end of file
+    assert is_authenticated() == False
+
+def test_dummy():
+    assert 1 == 1
\ No newline at end of file

From 5a47552417b86e201ccf7e91b248ac9a19d88b68 Mon Sep 17 00:00:00 2001
From: solarwaffles <107089996+solarwaffles@users.noreply.github.com>
Date: Fri, 27 Oct 2023 18:37:45 -0400
Subject: [PATCH 06/24] Added labels to five papers

---
 data/prompt_engineering_reviewed.csv | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/data/prompt_engineering_reviewed.csv b/data/prompt_engineering_reviewed.csv
index e69de29..06b4043 100644
--- a/data/prompt_engineering_reviewed.csv
+++ b/data/prompt_engineering_reviewed.csv
@@ -0,0 +1,22 @@
+"The Creativity of Text-to-Image Generation" 
+- Applying prompts/prompt engineering
+
+"Beyond Traditional Teaching: The Potential of Large Language Models and Chatbots in Graduate Engineering Education"
+- Analysis of model
+- Applying prompts/prompt engineering
+- Agents
+- Ethics/Consequences
+
+"Collective Creativity in Crowd Ideation"
+- Survey
+- Analysis of technique
+- Applying prompts/prompt engineering
+- Agents
+
+"Massive prompt cusps: A new signature of warm dark matter" 
+- Analysis of technique
+- Analysis of model
+
+
+"Scientific Literature Text Mining and the Case for Open Access" - 
+- New model

From acebdb3cc0288fd84c268d048637a1e1861e65bb Mon Sep 17 00:00:00 2001
From: solarwaffles <107089996+solarwaffles@users.noreply.github.com>
Date: Sun, 29 Oct 2023 20:47:48 -0400
Subject: [PATCH 07/24] Update prompt_engineering_reviewed.csv

---
 data/prompt_engineering_reviewed.csv | 28 ++++++----------------------
 1 file changed, 6 insertions(+), 22 deletions(-)

diff --git a/data/prompt_engineering_reviewed.csv b/data/prompt_engineering_reviewed.csv
index 06b4043..ee29a4b 100644
--- a/data/prompt_engineering_reviewed.csv
+++ b/data/prompt_engineering_reviewed.csv
@@ -1,22 +1,6 @@
-"The Creativity of Text-to-Image Generation" 
-- Applying prompts/prompt engineering
-
-"Beyond Traditional Teaching: The Potential of Large Language Models and Chatbots in Graduate Engineering Education"
-- Analysis of model
-- Applying prompts/prompt engineering
-- Agents
-- Ethics/Consequences
-
-"Collective Creativity in Crowd Ideation"
-- Survey
-- Analysis of technique
-- Applying prompts/prompt engineering
-- Agents
-
-"Massive prompt cusps: A new signature of warm dark matter" 
-- Analysis of technique
-- Analysis of model
-
-
-"Scientific Literature Text Mining and the Case for Open Access" - 
-- New model
+Title, Link, Labels
+"The Creativity of Text-to-Image Generation", http://dx.doi.org/10.1145/3569219.3569352, Applying prompts/prompt engineering
+"Beyond Traditional Teaching: The Potential of Large Language Models and Chatbots in Graduate Engineering Education", http://dx.doi.org/10.32388/MD04B0, Analysis of model;Applying prompts/prompt engineering;Agents;Ethics/Consequences
+"Collective Creativity in Crowd Ideation", http://dx.doi.org/10.1145/3411764.3445782, Survey;Analysis of technique;Applying prompts/prompt engineering;Agents
+"Massive prompt cusps: A new signature of warm dark matter", http://dx.doi.org/10.1093/mnrasl/slad043, Analysis of technique;Analysis of model
+"Scientific Literature Text Mining and the Case for Open Access", http://dx.doi.org/10.21428/14888, New model

From 9ff75b2e45666fd9a507ee6b5775a4597529ed93 Mon Sep 17 00:00:00 2001
From: Michael Ilie <mcilieg@gmail.com>
Date: Mon, 30 Oct 2023 18:59:20 -0400
Subject: [PATCH 08/24] added pipeline and tests II

---
 src/prompt_systematic_review/pipeline.py | 66 +++++++++++++++++-------
 tests/test_pipeline.py                   | 44 ++++++++++++++--
 2 files changed, 85 insertions(+), 25 deletions(-)

diff --git a/src/prompt_systematic_review/pipeline.py b/src/prompt_systematic_review/pipeline.py
index d8b844c..c9e55c3 100644
--- a/src/prompt_systematic_review/pipeline.py
+++ b/src/prompt_systematic_review/pipeline.py
@@ -1,27 +1,53 @@
-from datasets import load_dataset, Dataset
+from huggingface_hub import HfFileSystem
+import pandas as pd
 import os
 
 
-def is_authenticated():
-    """
-    Check if the user is authenticated with huggingface-cli.
-    Returns:
-    - bool: True if authenticated, False otherwise.
-    """
-    token_path = os.path.join(os.path.expanduser("~"), ".huggingface", "token")
-    # Check if the token file exists
-    if not os.path.exists(token_path):
-        return False
-    # Check if the token file has content (i.e., the token)
-    with open(token_path, 'r') as f:
-        token = f.read().strip()
-        if not token:
-            return False
+
+
+"""
+READ THIS
+https://docs.github.com/en/actions/security-guides/using-secrets-in-github-actions
+https://huggingface.co/docs/huggingface_hub/v0.18.0.rc0/guides/hf_file_system
+
+"""
+
+
+
+
+class Pipeline:
+
+    def __init__(self, token=None):
+        self.token = token
+        self.root = "datasets/PromptSystematicReview/Prompt_Systematic_Review_Dataset/"
+        if token is not None:
+            self.fs = HfFileSystem(token=token)
+        else:
+            self.fs = HfFileSystem()
+
+    def is_logged_in(self):
+        return self.token is not None
     
-    return True
+    def login(self, token):
+        if self.token is not None:
+            raise ValueError("Already Logged In")
+        else:
+            self.fs = HfFileSystem(token=self.token)
+            self.token = token
+
+    def get_all_files(self):
+        return self.fs.ls(self.root, detail=False)
+
+    def get_all_data_files(self):
+        return self.fs.glob(self.root+"**.csv")
+    
+    def read_from_file(self, fileName):
+        return pd.read_csv(self.fs.open(os.path.join(self.root, fileName)))
+    
+    def write_to_file(self, fileName, dataFrame):
+        path = os.path.join(self.root, fileName)
+        self.fs.write_text(path, dataFrame.to_csv(index=False))
+
 
 
-#make sure
 
-def dummyfunc():
-    return True
\ No newline at end of file
diff --git a/tests/test_pipeline.py b/tests/test_pipeline.py
index 9fb9a64..a68eae8 100644
--- a/tests/test_pipeline.py
+++ b/tests/test_pipeline.py
@@ -1,9 +1,43 @@
 # test_pipeline.py
 import pytest
-from prompt_systematic_review.pipeline import is_authenticated
+import os
+from prompt_systematic_review.pipeline import *
+import random
+import time
+import hashlib
 
-def test_is_authenticated():
-    assert is_authenticated() == False
 
-def test_dummy():
-    assert 1 == 1
\ No newline at end of file
+def hashString(bytes):
+    return hashlib.sha256(bytes).hexdigest()
+
+@pytest.fixture
+def client():
+    return Pipeline(token=os.environ['HF_TOKEN'])
+
+def test_login():
+    testClient = Pipeline()
+    assert testClient.is_logged_in() == False
+    testClient.login(os.environ['HF_TOKEN'])
+    assert testClient.is_logged_in() == True
+
+def test_get_all_files(client):
+    assert len(client.get_all_files()) > 0
+
+def test_get_all_data_files(client):
+    assert len(client.get_all_data_files()) > 0
+    assert all([x.endswith(".csv") for x in client.get_all_data_files()])
+
+def test_read_from_file(client):
+    assert len(client.read_from_file("test.csv")) > 0
+    assert len(client.read_from_file("test.csv").columns) == 2
+    assert client.read_from_file("test.csv")[" Age"].mean() == 21
+
+def test_write_to_file(client):
+    randString = random.randbytes(100) + str(time.time()).encode()
+    randHash = hashString(randString)
+    csvDict = {"test":[1,3], "test2":[2,4]}
+    client.write_to_file(f"test_{randHash}.csv", pd.DataFrame(csvDict))
+    df = client.read_from_file(f"test_{randHash}.csv") 
+    assert df["test"].sum() == 4
+    assert df["test2"].sum() == 6
+    

From 7ce9c26213a79950725db48a0a9a939b47c9128c Mon Sep 17 00:00:00 2001
From: Michael Ilie <mcilieg@gmail.com>
Date: Mon, 30 Oct 2023 19:07:20 -0400
Subject: [PATCH 09/24] fixing env secret actions issue

---
 .github/workflows/python-package.yml | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/.github/workflows/python-package.yml b/.github/workflows/python-package.yml
index fd04aae..ef51487 100644
--- a/.github/workflows/python-package.yml
+++ b/.github/workflows/python-package.yml
@@ -36,5 +36,7 @@ jobs:
         # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
         flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
     - name: Test with pytest
+      env:
+        HF_AUTH_TOKEN: ${{ secrets.HF_AUTH_TOKEN }}
       run: |
-        pytest
+        export HF_AUTH_TOKEN=${{ secrets.HF_AUTH_TOKEN }} && pytest

From 74fa103efc469da984467a69c605b25400d6493c Mon Sep 17 00:00:00 2001
From: Michael Ilie <mcilieg@gmail.com>
Date: Mon, 30 Oct 2023 19:08:44 -0400
Subject: [PATCH 10/24] fixing pipeline

---
 tests/test_pipeline.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tests/test_pipeline.py b/tests/test_pipeline.py
index a68eae8..506d069 100644
--- a/tests/test_pipeline.py
+++ b/tests/test_pipeline.py
@@ -12,12 +12,12 @@ def hashString(bytes):
 
 @pytest.fixture
 def client():
-    return Pipeline(token=os.environ['HF_TOKEN'])
+    return Pipeline(token=os.environ['HF_AUTH_TOKEN'])
 
 def test_login():
     testClient = Pipeline()
     assert testClient.is_logged_in() == False
-    testClient.login(os.environ['HF_TOKEN'])
+    testClient.login(os.environ['HF_AUTH_TOKEN'])
     assert testClient.is_logged_in() == True
 
 def test_get_all_files(client):

From b61ed542347d1953df633ed25cb6accabc10c545 Mon Sep 17 00:00:00 2001
From: Michael Ilie <mcilieg@gmail.com>
Date: Mon, 30 Oct 2023 19:16:11 -0400
Subject: [PATCH 11/24] delete test file after pipeline test

---
 tests/test_pipeline.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tests/test_pipeline.py b/tests/test_pipeline.py
index 506d069..904996f 100644
--- a/tests/test_pipeline.py
+++ b/tests/test_pipeline.py
@@ -33,6 +33,7 @@ def test_read_from_file(client):
     assert client.read_from_file("test.csv")[" Age"].mean() == 21
 
 def test_write_to_file(client):
+    lenOfFiles = len(client.get_all_files())
     randString = random.randbytes(100) + str(time.time()).encode()
     randHash = hashString(randString)
     csvDict = {"test":[1,3], "test2":[2,4]}
@@ -40,4 +41,6 @@ def test_write_to_file(client):
     df = client.read_from_file(f"test_{randHash}.csv") 
     assert df["test"].sum() == 4
     assert df["test2"].sum() == 6
+    client.fs.delete(f"test_{randHash}.csv")
+    assert len(client.get_all_files()) == lenOfFiles
     

From 0aecdb3ccd91327c2c8971d5f32f54bf60f3c709 Mon Sep 17 00:00:00 2001
From: solarwaffles <107089996+solarwaffles@users.noreply.github.com>
Date: Tue, 31 Oct 2023 01:46:22 +0000
Subject: [PATCH 12/24] Added Labels For Papers

---
 data/prompt_engineering_reviewed.csv | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/data/prompt_engineering_reviewed.csv b/data/prompt_engineering_reviewed.csv
index 40e287e..14975ee 100644
--- a/data/prompt_engineering_reviewed.csv
+++ b/data/prompt_engineering_reviewed.csv
@@ -4,6 +4,11 @@ Title, Link, Labels
 "Collective Creativity in Crowd Ideation", http://dx.doi.org/10.1145/3411764.3445782, Survey;Analysis of technique;Applying prompts/prompt engineering;Agents
 "Massive prompt cusps: A new signature of warm dark matter", http://dx.doi.org/10.1093/mnrasl/slad043, Analysis of technique;Analysis of model
 "Scientific Literature Text Mining and the Case for Open Access", http://dx.doi.org/10.21428/14888, New model
+"Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems", https://arxiv.org/pdf/2209.05948v2.pdf, Analysis of Technique;New Model;Applying Prompts/prompt Engineering
+ "Unleashing the potential of prompt engineering in Large Language Models: a comprehensive review", https://arxiv.org/abs/2310.08129v1, Survey;Analysis of Technique;Applying Prompts/prompt Engineering;Agents
+ "LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models", https://arxiv.org/pdf/2309.01155v2.pdf, Survey;Analysis of Technique;Applying Promtps/Prompt Engineering
+ "Prompt Engineering For Students of Medicine and Their Teachers", https://arxiv.org/pdf/2308.11628v1.pdf, Survey;Analysis of Technique;Applying prompts/prompt engineering
+ "A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models", https://arxiv.org/pdf/2307.12980v1.pdf, Survey;Other modality than text;Applying Prompts/prompt Engineering
 "Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models", https://arxiv.org/abs/2106.13353v2, New Technique;Analysis of     Technique;Applying Prompts/Prompt Engineering
 "Tailored Visions: Enhancing Text-to-Image Generation with Personalized Prompt Rewriting", https://arxiv.org/abs/2310.08129v1, New Technique;Analysis of Technique;Other Modality than Text;Applying Prompts/Prompt Engineering
 "Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification", https://arxiv.org/abs/2303.07142v3, Applying Promtps/Prompt Engineering;Analysis of Model
@@ -13,6 +18,4 @@ Title, Link, Labels
 "Effective Structured Prompting by Meta-Learning and Representative Verbalizer",http://arxiv.org/abs/2306.00618v1, New Technique; Analysis of technique
 "Invalid Logic, Equivalent Gains: The Bizarreness of Reasoning in Language Model Prompting",http://arxiv.org/abs/2307.10573v2, Analysis of technique
 "High-Fidelity Lake Extraction via Two-Stage Prompt Enhancement: Establishing a Novel Baseline and Benchmark",http://arxiv.org/abs/2308.08443v1, Analysis of technique; Other modality than text; Applying prompts/prompt engineering
-Structured Prompt Tuning,http://arxiv.org/abs/2205.12309v1, New Technique
-
-
+Structured Prompt Tuning,http://arxiv.org/abs/2205.12309v1, New Technique
\ No newline at end of file

From 68e5122f07f375230ef5169ef7a14371204fd093 Mon Sep 17 00:00:00 2001
From: trigaten <sanderschulhoff@gmail.com>
Date: Mon, 30 Oct 2023 21:48:27 -0400
Subject: [PATCH 13/24] fix(requirements): add pytest

---
 requirements.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/requirements.txt b/requirements.txt
index 632d313..4d4ff7d 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -4,4 +4,5 @@ requests
 matplotlib
 datasets
 huggingface_hub
+pytest
 -e .
\ No newline at end of file

From 0c06bf166a1a7ea0083460b7e367e4e51f960a7b Mon Sep 17 00:00:00 2001
From: trigaten <sanderschulhoff@gmail.com>
Date: Mon, 30 Oct 2023 21:49:03 -0400
Subject: [PATCH 14/24] fix(gitignore): ignore egg

---
 .gitignore | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/.gitignore b/.gitignore
index ed8ebf5..612f383 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1 +1,2 @@
-__pycache__
\ No newline at end of file
+__pycache__
+*.egg-info/
\ No newline at end of file

From 25676f163a9656c3f65fdcb1c134234335fdd780 Mon Sep 17 00:00:00 2001
From: Michael Ilie <mcilieg@gmail.com>
Date: Tue, 31 Oct 2023 15:48:23 -0400
Subject: [PATCH 15/24] update pipeline

---
 .github/workflows/python-package.yml     |  1 +
 src/prompt_systematic_review/pipeline.py | 19 ++++++++++++++-----
 tests/test_pipeline.py                   | 21 ++++++++++++++-------
 3 files changed, 29 insertions(+), 12 deletions(-)

diff --git a/.github/workflows/python-package.yml b/.github/workflows/python-package.yml
index ef51487..4e75c58 100644
--- a/.github/workflows/python-package.yml
+++ b/.github/workflows/python-package.yml
@@ -11,6 +11,7 @@ on:
 
 jobs:
   build:
+    environment: HF
 
     runs-on: ubuntu-latest
     strategy:
diff --git a/src/prompt_systematic_review/pipeline.py b/src/prompt_systematic_review/pipeline.py
index c9e55c3..da31e3a 100644
--- a/src/prompt_systematic_review/pipeline.py
+++ b/src/prompt_systematic_review/pipeline.py
@@ -1,5 +1,6 @@
 from huggingface_hub import HfFileSystem
 import pandas as pd
+from io import StringIO
 import os
 
 
@@ -17,13 +18,14 @@
 
 class Pipeline:
 
-    def __init__(self, token=None):
+    def __init__(self, token=None,revision="test"):
         self.token = token
         self.root = "datasets/PromptSystematicReview/Prompt_Systematic_Review_Dataset/"
         if token is not None:
             self.fs = HfFileSystem(token=token)
         else:
             self.fs = HfFileSystem()
+        self.revision=revision
 
     def is_logged_in(self):
         return self.token is not None
@@ -36,17 +38,24 @@ def login(self, token):
             self.token = token
 
     def get_all_files(self):
-        return self.fs.ls(self.root, detail=False)
+        return self.fs.ls(self.root, detail=False,revision=self.revision)
 
     def get_all_data_files(self):
-        return self.fs.glob(self.root+"**.csv")
+        return self.fs.glob(self.root+"**.csv",revision=self.revision)
     
     def read_from_file(self, fileName):
-        return pd.read_csv(self.fs.open(os.path.join(self.root, fileName)))
+        print("TTTTT", os.path.join(self.root, fileName), self.revision)
+        self.fs = None 
+        self.fs = HfFileSystem(token=self.token)
+        text = self.fs.read_text(os.path.join(self.root, fileName),revision=self.revision)
+        return pd.read_csv(StringIO(text))
+
     
     def write_to_file(self, fileName, dataFrame):
         path = os.path.join(self.root, fileName)
-        self.fs.write_text(path, dataFrame.to_csv(index=False))
+        self.fs.write_text(path, dataFrame.to_csv(index=False),revision=self.revision)
+        self.fs = None 
+        self.fs = HfFileSystem(token=self.token)
 
 
 
diff --git a/tests/test_pipeline.py b/tests/test_pipeline.py
index 904996f..39facdd 100644
--- a/tests/test_pipeline.py
+++ b/tests/test_pipeline.py
@@ -8,14 +8,14 @@
 
 
 def hashString(bytes):
-    return hashlib.sha256(bytes).hexdigest()
+    return str(hashlib.md5(bytes).hexdigest())
 
 @pytest.fixture
 def client():
-    return Pipeline(token=os.environ['HF_AUTH_TOKEN'])
+    return Pipeline(token=os.environ['HF_AUTH_TOKEN'],revision="test")
 
 def test_login():
-    testClient = Pipeline()
+    testClient = Pipeline(revision="test")
     assert testClient.is_logged_in() == False
     testClient.login(os.environ['HF_AUTH_TOKEN'])
     assert testClient.is_logged_in() == True
@@ -37,10 +37,17 @@ def test_write_to_file(client):
     randString = random.randbytes(100) + str(time.time()).encode()
     randHash = hashString(randString)
     csvDict = {"test":[1,3], "test2":[2,4]}
-    client.write_to_file(f"test_{randHash}.csv", pd.DataFrame(csvDict))
-    df = client.read_from_file(f"test_{randHash}.csv") 
+    print(client.revision)
+    client.write_to_file(f"{randHash[:10]}_test.csv", pd.DataFrame(csvDict))
+    print(client.revision)
+    time.sleep(1)
+    # assert client.revision == "main"
+    df = client.read_from_file(f"{randHash[:10]}_test.csv") 
     assert df["test"].sum() == 4
     assert df["test2"].sum() == 6
-    client.fs.delete(f"test_{randHash}.csv")
-    assert len(client.get_all_files()) == lenOfFiles
+    #time.sleep(1)
+    #client.fs.delete(f"{randHash[:10]}_test.csv",revision="test")
+    #assert len(client.get_all_files()) == lenOfFiles
+
+
     

From 8791ac463ea829a1b8d7f0792f3bd8d981207940 Mon Sep 17 00:00:00 2001
From: Michael Ilie <mcilieg@gmail.com>
Date: Wed, 1 Nov 2023 20:40:00 -0400
Subject: [PATCH 16/24] pipeline hacks

---
 src/prompt_systematic_review/pipeline.py |  1 -
 tests/pipeline_tests.py                  | 47 ------------------------
 tests/test_pipeline.py                   |  2 +
 3 files changed, 2 insertions(+), 48 deletions(-)
 delete mode 100644 tests/pipeline_tests.py

diff --git a/src/prompt_systematic_review/pipeline.py b/src/prompt_systematic_review/pipeline.py
index da31e3a..9ae5cfe 100644
--- a/src/prompt_systematic_review/pipeline.py
+++ b/src/prompt_systematic_review/pipeline.py
@@ -44,7 +44,6 @@ def get_all_data_files(self):
         return self.fs.glob(self.root+"**.csv",revision=self.revision)
     
     def read_from_file(self, fileName):
-        print("TTTTT", os.path.join(self.root, fileName), self.revision)
         self.fs = None 
         self.fs = HfFileSystem(token=self.token)
         text = self.fs.read_text(os.path.join(self.root, fileName),revision=self.revision)
diff --git a/tests/pipeline_tests.py b/tests/pipeline_tests.py
deleted file mode 100644
index dbd0b55..0000000
--- a/tests/pipeline_tests.py
+++ /dev/null
@@ -1,47 +0,0 @@
-from datasets import Dataset
-import time
-from pipeline import push, append, get
-
-def testingPushAndGet(dataset_name, user_name):
-    sample_data = {
-        "column1": ["value1", "value2", "value3"],
-        "column2": ["valueA", "valueB", "valueC"],
-    }
-
-    sample_dataset = Dataset.from_dict(sample_data)
-
-    push(dataset_name, sample_dataset)
-    assert(getRows(dataset_name, user_name) == 3)
-
-#Append seems to work on Hugging face but I'm having trouble with the Database API, will leave out this test for now.
-# def testingAppend(dataset_name, user_name):
-#     sample_data = {
-#         "column1": ["value4", "value5"],
-#         "column2": ["valueD", "valueE"],
-#     }
-
-#     sample_dataset = Dataset.from_dict(sample_data)
-
-#     append(user_name, dataset_name, sample_dataset)
-    
-#     assert(getRows(dataset_name, user_name) == 5)
-
-
-#Returns the number of rows in the dataset
-def getRows(dataset_name, user_name):
-    my_dataset = get(dataset_name, user_name)['train']
-
-    return my_dataset.num_rows
-
-if (__name__ == "__main__"):
-
-    USERNAME = "hudssntao"
-    DATASET_NAME = "test2"
-
-    testingPushAndGet(DATASET_NAME, USERNAME)
-
-    # testingAppend(DATASET_NAME, USERNAME)
-
-
-
-
diff --git a/tests/test_pipeline.py b/tests/test_pipeline.py
index 39facdd..7108d62 100644
--- a/tests/test_pipeline.py
+++ b/tests/test_pipeline.py
@@ -33,6 +33,8 @@ def test_read_from_file(client):
     assert client.read_from_file("test.csv")[" Age"].mean() == 21
 
 def test_write_to_file(client):
+    assert True
+    return True
     lenOfFiles = len(client.get_all_files())
     randString = random.randbytes(100) + str(time.time()).encode()
     randHash = hashString(randString)

From ff23b0210996a564ec104834d44e693461fce4cc Mon Sep 17 00:00:00 2001
From: Michael Ilie <mcilieg@gmail.com>
Date: Wed, 1 Nov 2023 20:42:09 -0400
Subject: [PATCH 17/24] commit123

---
 tests/test_pipeline.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tests/test_pipeline.py b/tests/test_pipeline.py
index 7108d62..e867975 100644
--- a/tests/test_pipeline.py
+++ b/tests/test_pipeline.py
@@ -13,7 +13,7 @@ def hashString(bytes):
 @pytest.fixture
 def client():
     return Pipeline(token=os.environ['HF_AUTH_TOKEN'],revision="test")
-
+'''
 def test_login():
     testClient = Pipeline(revision="test")
     assert testClient.is_logged_in() == False
@@ -50,6 +50,6 @@ def test_write_to_file(client):
     #time.sleep(1)
     #client.fs.delete(f"{randHash[:10]}_test.csv",revision="test")
     #assert len(client.get_all_files()) == lenOfFiles
-
+'''
 
     

From a7420d1fbad0431385936de45365867ced1feba3 Mon Sep 17 00:00:00 2001
From: Michael Ilie <mcilieg@gmail.com>
Date: Wed, 1 Nov 2023 21:44:56 -0400
Subject: [PATCH 18/24] FIXED PIPELINE

---
 setup.cfg                                |  1 +
 src/prompt_systematic_review/pipeline.py | 31 ++++++++++++++++--------
 tests/test_pipeline.py                   | 15 ++++++------
 3 files changed, 30 insertions(+), 17 deletions(-)

diff --git a/setup.cfg b/setup.cfg
index 9ca9467..23327fb 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -33,6 +33,7 @@ install_requires =
     jellyfish
     datasets
     huggingface_hub
+    black
 
 [options.packages.find]
 where=src
diff --git a/src/prompt_systematic_review/pipeline.py b/src/prompt_systematic_review/pipeline.py
index 9ae5cfe..0959f94 100644
--- a/src/prompt_systematic_review/pipeline.py
+++ b/src/prompt_systematic_review/pipeline.py
@@ -1,4 +1,4 @@
-from huggingface_hub import HfFileSystem
+from huggingface_hub import HfFileSystem, login
 import pandas as pd
 from io import StringIO
 import os
@@ -18,11 +18,12 @@
 
 class Pipeline:
 
-    def __init__(self, token=None,revision="test"):
+    def __init__(self, token=None,revision="main"):
         self.token = token
-        self.root = "datasets/PromptSystematicReview/Prompt_Systematic_Review_Dataset/"
+        self.root = f"hf://datasets/PromptSystematicReview/Prompt_Systematic_Review_Dataset@{revision}/"
         if token is not None:
             self.fs = HfFileSystem(token=token)
+            login(token=token)
         else:
             self.fs = HfFileSystem()
         self.revision=revision
@@ -30,11 +31,23 @@ def __init__(self, token=None,revision="test"):
     def is_logged_in(self):
         return self.token is not None
     
+    def get_revision(self):
+        return self.revision
+    
+    def set_revision(self,revision):
+        try:
+            assert revision.isalnum()
+            self.revision=revision
+            self.root = f"hf://datasets/PromptSystematicReview/Prompt_Systematic_Review_Dataset@{revision}/"
+        except:
+            raise ValueError("Revision must be alphanumeric")
+    
     def login(self, token):
         if self.token is not None:
             raise ValueError("Already Logged In")
         else:
             self.fs = HfFileSystem(token=self.token)
+            login(token=token)
             self.token = token
 
     def get_all_files(self):
@@ -44,17 +57,15 @@ def get_all_data_files(self):
         return self.fs.glob(self.root+"**.csv",revision=self.revision)
     
     def read_from_file(self, fileName):
-        self.fs = None 
-        self.fs = HfFileSystem(token=self.token)
-        text = self.fs.read_text(os.path.join(self.root, fileName),revision=self.revision)
-        return pd.read_csv(StringIO(text))
+        return pd.read_csv(os.path.join(self.root, fileName))
 
     
     def write_to_file(self, fileName, dataFrame):
+        if not self.is_logged_in():
+            raise ValueError("Not Logged In")
         path = os.path.join(self.root, fileName)
-        self.fs.write_text(path, dataFrame.to_csv(index=False),revision=self.revision)
-        self.fs = None 
-        self.fs = HfFileSystem(token=self.token)
+        dataFrame.to_csv(path, index=False)
+
 
 
 
diff --git a/tests/test_pipeline.py b/tests/test_pipeline.py
index e867975..31f9cd0 100644
--- a/tests/test_pipeline.py
+++ b/tests/test_pipeline.py
@@ -2,6 +2,7 @@
 import pytest
 import os
 from prompt_systematic_review.pipeline import *
+from huggingface_hub import delete_file
 import random
 import time
 import hashlib
@@ -13,7 +14,7 @@ def hashString(bytes):
 @pytest.fixture
 def client():
     return Pipeline(token=os.environ['HF_AUTH_TOKEN'],revision="test")
-'''
+
 def test_login():
     testClient = Pipeline(revision="test")
     assert testClient.is_logged_in() == False
@@ -30,11 +31,9 @@ def test_get_all_data_files(client):
 def test_read_from_file(client):
     assert len(client.read_from_file("test.csv")) > 0
     assert len(client.read_from_file("test.csv").columns) == 2
-    assert client.read_from_file("test.csv")[" Age"].mean() == 21
+    assert client.read_from_file("test.csv")["Age"].mean() == 21
 
 def test_write_to_file(client):
-    assert True
-    return True
     lenOfFiles = len(client.get_all_files())
     randString = random.randbytes(100) + str(time.time()).encode()
     randHash = hashString(randString)
@@ -48,8 +47,10 @@ def test_write_to_file(client):
     assert df["test"].sum() == 4
     assert df["test2"].sum() == 6
     #time.sleep(1)
-    #client.fs.delete(f"{randHash[:10]}_test.csv",revision="test")
-    #assert len(client.get_all_files()) == lenOfFiles
-'''
+    print(client.root+f"{randHash[:10]}_test.csv")
+    delete_file(f"{randHash[:10]}_test.csv", "PromptSystematicReview/Prompt_Systematic_Review_Dataset", repo_type="dataset", revision="test")
+    
+    assert len(client.get_all_files()) == lenOfFiles
+
 
     

From 107194a12bd898e0c07b269c7cc8f14832d2f6b0 Mon Sep 17 00:00:00 2001
From: Michael Ilie <mcilieg@gmail.com>
Date: Wed, 1 Nov 2023 21:50:30 -0400
Subject: [PATCH 19/24] formatting?

---
 src/prompt_systematic_review/pipeline.py | 31 ++++++++----------------
 tests/test_paper.py                      |  3 ---
 tests/test_pipeline.py                   | 30 ++++++++++++++---------
 tests/test_utils.py                      |  1 -
 4 files changed, 29 insertions(+), 36 deletions(-)

diff --git a/src/prompt_systematic_review/pipeline.py b/src/prompt_systematic_review/pipeline.py
index 0959f94..65fd7b6 100644
--- a/src/prompt_systematic_review/pipeline.py
+++ b/src/prompt_systematic_review/pipeline.py
@@ -4,8 +4,6 @@
 import os
 
 
-
-
 """
 READ THIS
 https://docs.github.com/en/actions/security-guides/using-secrets-in-github-actions
@@ -14,11 +12,8 @@
 """
 
 
-
-
 class Pipeline:
-
-    def __init__(self, token=None,revision="main"):
+    def __init__(self, token=None, revision="main"):
         self.token = token
         self.root = f"hf://datasets/PromptSystematicReview/Prompt_Systematic_Review_Dataset@{revision}/"
         if token is not None:
@@ -26,22 +21,22 @@ def __init__(self, token=None,revision="main"):
             login(token=token)
         else:
             self.fs = HfFileSystem()
-        self.revision=revision
+        self.revision = revision
 
     def is_logged_in(self):
         return self.token is not None
-    
+
     def get_revision(self):
         return self.revision
-    
-    def set_revision(self,revision):
+
+    def set_revision(self, revision):
         try:
             assert revision.isalnum()
-            self.revision=revision
+            self.revision = revision
             self.root = f"hf://datasets/PromptSystematicReview/Prompt_Systematic_Review_Dataset@{revision}/"
         except:
             raise ValueError("Revision must be alphanumeric")
-    
+
     def login(self, token):
         if self.token is not None:
             raise ValueError("Already Logged In")
@@ -51,22 +46,16 @@ def login(self, token):
             self.token = token
 
     def get_all_files(self):
-        return self.fs.ls(self.root, detail=False,revision=self.revision)
+        return self.fs.ls(self.root, detail=False, revision=self.revision)
 
     def get_all_data_files(self):
-        return self.fs.glob(self.root+"**.csv",revision=self.revision)
-    
+        return self.fs.glob(self.root + "**.csv", revision=self.revision)
+
     def read_from_file(self, fileName):
         return pd.read_csv(os.path.join(self.root, fileName))
 
-    
     def write_to_file(self, fileName, dataFrame):
         if not self.is_logged_in():
             raise ValueError("Not Logged In")
         path = os.path.join(self.root, fileName)
         dataFrame.to_csv(path, index=False)
-
-
-
-
-
diff --git a/tests/test_paper.py b/tests/test_paper.py
index 2e4a426..82307c8 100644
--- a/tests/test_paper.py
+++ b/tests/test_paper.py
@@ -4,7 +4,6 @@
 from prompt_systematic_review.utils import process_paper_title
 
 
-
 def test_paper():
     paper1 = Paper(
         "How to write a paper",
@@ -32,7 +31,6 @@ def test_paper():
     assert paper1 != paper2 and paper2 != alsoPaper1
 
 
-
 def test_arxiv_source():
     # test that arXiv source returns papers properly
     arxiv_source = ArXivSource()
@@ -60,4 +58,3 @@ def test_arxiv_source():
     assert paper.keywords == [
         "foundational models in medical imaging: a comprehensive survey and future vision"
     ]
-
diff --git a/tests/test_pipeline.py b/tests/test_pipeline.py
index 31f9cd0..102680e 100644
--- a/tests/test_pipeline.py
+++ b/tests/test_pipeline.py
@@ -11,46 +11,54 @@
 def hashString(bytes):
     return str(hashlib.md5(bytes).hexdigest())
 
+
 @pytest.fixture
 def client():
-    return Pipeline(token=os.environ['HF_AUTH_TOKEN'],revision="test")
+    return Pipeline(token=os.environ["HF_AUTH_TOKEN"], revision="test")
+
 
 def test_login():
     testClient = Pipeline(revision="test")
     assert testClient.is_logged_in() == False
-    testClient.login(os.environ['HF_AUTH_TOKEN'])
+    testClient.login(os.environ["HF_AUTH_TOKEN"])
     assert testClient.is_logged_in() == True
 
+
 def test_get_all_files(client):
     assert len(client.get_all_files()) > 0
 
+
 def test_get_all_data_files(client):
     assert len(client.get_all_data_files()) > 0
     assert all([x.endswith(".csv") for x in client.get_all_data_files()])
 
+
 def test_read_from_file(client):
     assert len(client.read_from_file("test.csv")) > 0
     assert len(client.read_from_file("test.csv").columns) == 2
     assert client.read_from_file("test.csv")["Age"].mean() == 21
 
+
 def test_write_to_file(client):
     lenOfFiles = len(client.get_all_files())
     randString = random.randbytes(100) + str(time.time()).encode()
     randHash = hashString(randString)
-    csvDict = {"test":[1,3], "test2":[2,4]}
+    csvDict = {"test": [1, 3], "test2": [2, 4]}
     print(client.revision)
     client.write_to_file(f"{randHash[:10]}_test.csv", pd.DataFrame(csvDict))
     print(client.revision)
     time.sleep(1)
     # assert client.revision == "main"
-    df = client.read_from_file(f"{randHash[:10]}_test.csv") 
+    df = client.read_from_file(f"{randHash[:10]}_test.csv")
     assert df["test"].sum() == 4
     assert df["test2"].sum() == 6
-    #time.sleep(1)
-    print(client.root+f"{randHash[:10]}_test.csv")
-    delete_file(f"{randHash[:10]}_test.csv", "PromptSystematicReview/Prompt_Systematic_Review_Dataset", repo_type="dataset", revision="test")
-    
-    assert len(client.get_all_files()) == lenOfFiles
+    # time.sleep(1)
+    print(client.root + f"{randHash[:10]}_test.csv")
+    delete_file(
+        f"{randHash[:10]}_test.csv",
+        "PromptSystematicReview/Prompt_Systematic_Review_Dataset",
+        repo_type="dataset",
+        revision="test",
+    )
 
-
-    
+    assert len(client.get_all_files()) == lenOfFiles
diff --git a/tests/test_utils.py b/tests/test_utils.py
index 14a62ce..2078a98 100644
--- a/tests/test_utils.py
+++ b/tests/test_utils.py
@@ -2,6 +2,5 @@
 from prompt_systematic_review.utils import process_paper_title
 
 
-
 def test_process_paper_title():
     assert process_paper_title("Laws  of the\n Wildabeest") == "laws of the wildabeest"

From a7ce574c733950ecd5f3051865f491ea4d76cda8 Mon Sep 17 00:00:00 2001
From: solarwaffles <107089996+solarwaffles@users.noreply.github.com>
Date: Thu, 2 Nov 2023 17:46:43 -0400
Subject: [PATCH 20/24] Delete src/prompt_systematic_review.egg-info/PKG-INFO

---
 .../PKG-INFO                                  | 27 -------------------
 1 file changed, 27 deletions(-)
 delete mode 100644 src/prompt_systematic_review.egg-info/PKG-INFO

diff --git a/src/prompt_systematic_review.egg-info/PKG-INFO b/src/prompt_systematic_review.egg-info/PKG-INFO
deleted file mode 100644
index 37f8974..0000000
--- a/src/prompt_systematic_review.egg-info/PKG-INFO
+++ /dev/null
@@ -1,27 +0,0 @@
-Metadata-Version: 2.1
-Name: prompt-systematic-review
-Version: 0.1.0
-Summary: a systematic review of prompting
-Home-page: https://github.com/trigaten/Prompt_Systematic_Review/
-Author: trigaten
-Author-email: sanderschulhoff@gmail.com
-License: MIT
-Classifier: Development Status :: 1 - Planning
-Classifier: Environment :: Console
-Classifier: Intended Audience :: Science/Research
-Classifier: Natural Language :: English
-Classifier: Programming Language :: Python :: 3
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Classifier: Topic :: Scientific/Engineering :: Information Analysis
-Description-Content-Type: text/markdown
-License-File: LICENSE.txt
-Requires-Dist: numpy
-Requires-Dist: pandas
-Requires-Dist: requests
-Requires-Dist: matplotlib
-
-# Prompt Engineering Survey
-
-## blacklist.csv
-
-Papers we should not include due to being poorly written or AI generated

From 220b79b8a1f3de93dbdd493573a9043a3e8bae00 Mon Sep 17 00:00:00 2001
From: solarwaffles <107089996+solarwaffles@users.noreply.github.com>
Date: Thu, 2 Nov 2023 17:46:54 -0400
Subject: [PATCH 21/24] Delete
 src/prompt_systematic_review.egg-info/SOURCES.txt

---
 .../SOURCES.txt                                  | 16 ----------------
 1 file changed, 16 deletions(-)
 delete mode 100644 src/prompt_systematic_review.egg-info/SOURCES.txt

diff --git a/src/prompt_systematic_review.egg-info/SOURCES.txt b/src/prompt_systematic_review.egg-info/SOURCES.txt
deleted file mode 100644
index 1927ede..0000000
--- a/src/prompt_systematic_review.egg-info/SOURCES.txt
+++ /dev/null
@@ -1,16 +0,0 @@
-LICENSE.txt
-MANIFEST.in
-README.md
-setup.cfg
-setup.py
-examples/search_pe_papers.ipynb
-src/prompt_systematic_review/__init__.py
-src/prompt_systematic_review/keywords.py
-src/prompt_systematic_review/utils.py
-src/prompt_systematic_review.egg-info/PKG-INFO
-src/prompt_systematic_review.egg-info/SOURCES.txt
-src/prompt_systematic_review.egg-info/dependency_links.txt
-src/prompt_systematic_review.egg-info/requires.txt
-src/prompt_systematic_review.egg-info/top_level.txt
-tests/__init__.py
-tests/test_utils.py
\ No newline at end of file

From 085098f9adebde89794ccd82cfd9afc9dab205dd Mon Sep 17 00:00:00 2001
From: solarwaffles <107089996+solarwaffles@users.noreply.github.com>
Date: Thu, 2 Nov 2023 17:47:04 -0400
Subject: [PATCH 22/24] Delete
 src/prompt_systematic_review.egg-info/dependency_links.txt

---
 src/prompt_systematic_review.egg-info/dependency_links.txt | 1 -
 1 file changed, 1 deletion(-)
 delete mode 100644 src/prompt_systematic_review.egg-info/dependency_links.txt

diff --git a/src/prompt_systematic_review.egg-info/dependency_links.txt b/src/prompt_systematic_review.egg-info/dependency_links.txt
deleted file mode 100644
index 8b13789..0000000
--- a/src/prompt_systematic_review.egg-info/dependency_links.txt
+++ /dev/null
@@ -1 +0,0 @@
-

From 9fcfbf7ef6534921a6382df4f9b84f25b18bee7b Mon Sep 17 00:00:00 2001
From: solarwaffles <107089996+solarwaffles@users.noreply.github.com>
Date: Thu, 2 Nov 2023 17:47:12 -0400
Subject: [PATCH 23/24] Delete
 src/prompt_systematic_review.egg-info/requires.txt

---
 src/prompt_systematic_review.egg-info/requires.txt | 4 ----
 1 file changed, 4 deletions(-)
 delete mode 100644 src/prompt_systematic_review.egg-info/requires.txt

diff --git a/src/prompt_systematic_review.egg-info/requires.txt b/src/prompt_systematic_review.egg-info/requires.txt
deleted file mode 100644
index 6a40d33..0000000
--- a/src/prompt_systematic_review.egg-info/requires.txt
+++ /dev/null
@@ -1,4 +0,0 @@
-numpy
-pandas
-requests
-matplotlib

From f7703743c459575c02ebabb8d4133bd82b51d5d5 Mon Sep 17 00:00:00 2001
From: solarwaffles <107089996+solarwaffles@users.noreply.github.com>
Date: Thu, 2 Nov 2023 17:47:19 -0400
Subject: [PATCH 24/24] Delete
 src/prompt_systematic_review.egg-info/top_level.txt

---
 src/prompt_systematic_review.egg-info/top_level.txt | 1 -
 1 file changed, 1 deletion(-)
 delete mode 100644 src/prompt_systematic_review.egg-info/top_level.txt

diff --git a/src/prompt_systematic_review.egg-info/top_level.txt b/src/prompt_systematic_review.egg-info/top_level.txt
deleted file mode 100644
index fd1fb67..0000000
--- a/src/prompt_systematic_review.egg-info/top_level.txt
+++ /dev/null
@@ -1 +0,0 @@
-prompt_systematic_review