Upload 11 files

.gitignore

@@ -0,0 +1,132 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# jetbrains
+.idea/

Functionalities/KeywordAdgroupPredict.py

@@ -0,0 +1,67 @@
+import numpy as np
+import pandas as pd
+
+from Functionalities import NLP_Helper
+
+
+class KeywordAdgroupPredict:
+
+    def predict_ad_group_for_keywords(self, candidate_kw_df, cur_kw_df, features, new_kw_col,
+                cur_kw_col, cur_adg_col, cur_camp_col, extra_stopwords=['_']) -> pd.DataFrame:
+        """
+        predicts ad group from current keyword and their ad groups
+        :param candidate_kw_df: keywords dataframe that we want to predict ad groups for
+        :param cur_kw_df: keywords details dataframe from current campaign
+        :param features: features/columns to use for finding relevancy
+        :param new_kw_col: the column in candidate_kw_df which holds the keywords
+        :param cur_kw_col: the column in cur_kw_df which holds the keywords
+        :param cur_adg_col: the column in cur_kw_df which holds the corresponding ad groups
+        :param cur_camp_col: the column in cur_kw_df which holds the corresponding campaigns
+        :param extra_stopwords: any extra terms that we want to avoid while finding relevancy
+        :return: dataframe similar to candidate_kw_df with two extra columns ['Recommended Ad group', 'relevance score']
+        """
+        output_cols = list(candidate_kw_df.columns) + ['Recommended Ad group', 'relevance score']
+
+        sentence_model = NLP_Helper.get_embedding_model()
+
+        cur_kw_df = cur_kw_df[[cur_kw_col, cur_adg_col, cur_camp_col]]
+
+        # cleanup
+        cur_kw_df[cur_kw_col].replace('[\[\]\"\']', '', regex=True, inplace=True)
+
+        # joining features per ad group to one column, for vectorization step
+        cur_kw_df = cur_kw_df.groupby([cur_camp_col, cur_adg_col]).agg(
+            {cur_kw_col: ', '.join}).reset_index()
+        cur_kw_df['Ad group contents'] = cur_kw_df[features].astype(str).agg(' ,'.join, axis=1)
+
+        NLP_Helper.remove_unnecessary_tokens_from_df(cur_kw_df, ['Ad group contents'],
+                                                          extra_stopwords=extra_stopwords)
+
+        # vectorization
+        candidate_kw_df['Keyword vector'] = NLP_Helper.str_to_vector_list(
+            candidate_kw_df[new_kw_col].tolist(), sentence_model)
+        cur_kw_df['Ad group vector'] = NLP_Helper.str_to_vector_list(
+            cur_kw_df['Ad group contents'].tolist(), sentence_model)
+
+        # cosine similarity calc
+        cosine_sim_matrix = NLP_Helper.cosine_sim_matrix(candidate_kw_df['Keyword vector'],
+                                                              cur_kw_df['Ad group vector'])
+        cosine_sim_max_indices = np.argmax(cosine_sim_matrix, axis=1)
+        cosine_sim_max_values = np.amax(cosine_sim_matrix, axis=1)
+        selected_ad_groups = cur_kw_df.iloc[cosine_sim_max_indices]
+        selected_ad_groups['relevance score'] = cosine_sim_max_values
+        selected_ad_groups.rename(columns={cur_adg_col: 'Recommended Ad group'}, inplace=True)
+        selected_ad_groups.reset_index(inplace=True)
+
+        # merge the columns
+        new_kw_adgroup_relevance_df = pd.concat([candidate_kw_df,
+                                                 selected_ad_groups[['Recommended Ad group', 'relevance score']]],
+                                                axis=1)
+
+        new_kw_adgroup_relevance_df = new_kw_adgroup_relevance_df[list(output_cols)]
+
+        new_kw_adgroup_relevance_df['relevance score'] = new_kw_adgroup_relevance_df['relevance score'].astype(float)
+        new_kw_adgroup_relevance_df = new_kw_adgroup_relevance_df.sort_values(by='relevance score',
+                                                                              ascending=False)
+
+        return new_kw_adgroup_relevance_df

Functionalities/NLP_Helper.py

@@ -0,0 +1,107 @@
+import numpy as np
+from sentence_transformers import SentenceTransformer, util
+from bertopic.representation import KeyBERTInspired, MaximalMarginalRelevance
+import nltk
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
+import string
+import re
+
+nltk.download('stopwords')
+nltk.download('punkt')
+
+STOP_WORDS = list(stopwords.words('english'))
+BERTOPIC_REPRESENTATIONS = [
+    "KeyBERTInspired",
+    "MaximalMarginalRelevance",
+]
+
+TRANSFORMERS = ["all-mpnet-base-v2", "multi-qa-mpnet-base-dot-v1"]
+TRANSFORMERS_INFO = ["all-mpnet-base-v2: All-round model tuned for many use-cases. "
+                     "Trained on a large and diverse dataset of over 1 billion training pairs",
+
+                     "multi-qa-mpnet-base-dot-v1: This model was tuned for semantic search: Given a query/question, "
+                     "if can find relevant passages. "
+                     "It was trained on a large and diverse set of (question, answer) pairs."
+                     ]
+
+
+def get_bertopic_representation(representation: str):
+    if representation == BERTOPIC_REPRESENTATIONS[0]:
+        return KeyBERTInspired()
+    elif representation == BERTOPIC_REPRESENTATIONS[1]:
+        return MaximalMarginalRelevance()
+    else:
+        return None
+
+
+def tokenize_explode(df, col):
+    df['tokenized'] = df[col].apply(word_tokenize)
+    df = df.explode('tokenized')
+    df['tokenized'] = df['tokenized'].str.strip()
+    df['tokenized'] = df['tokenized'].str.lower()
+
+    return df
+
+
+def cleanup_tokens(df, col):
+    df = df[df[col].apply(lambda x: len(x) > 2)]
+    df = df[~df[col].str.contains(r'^(\d+\.?\d*)$', regex=True)]
+    df = df[~df[col].isin([p for p in string.punctuation])]
+    df = df[df[col].isin(STOP_WORDS) == False]
+
+    return df
+
+
+def get_embedding_model(transformer=BERTOPIC_REPRESENTATIONS[0]) -> SentenceTransformer:
+    """
+    get given sentence transformer model
+    :param transformer:
+    :return:
+    """
+    sentence_model = SentenceTransformer(transformer)
+    return sentence_model
+
+
+def str_to_vector_list(text_list, sentence_model, replace_dict=None):
+    """
+    embedding for the given text list using provided embedding model
+    :param text_list:
+    :param sentence_model:
+    :param replace_dict: any values in the string that we may need to replace
+    :return:
+    """
+    text_list = [str(x).replace('[^\w\s]', '') for x in text_list]
+    if replace_dict:
+        for stp in replace_dict:
+            text_list = [str(x).replace(stp, replace_dict[stp]) for x in text_list]
+
+    embeddings = sentence_model.encode(text_list, show_progress_bar=True, batch_size=1000)
+    return embeddings.tolist()
+
+
+def remove_unnecessary_tokens_from_df(df, columns, extra_stopwords=None) -> None:
+    """
+    removes unnecessary token from the given columns of the dataframe
+    :param df:
+    :param columns:
+    :param extra_stopwords:
+    :return:
+    """
+    df[columns] = df[columns].apply(lambda x: x.str.replace('[^\w\s]', ''))
+
+    if extra_stopwords:
+        for stp in extra_stopwords:
+            df[columns] = df[columns].apply(lambda x: x.str.replace(stp, ' '))
+
+
+def cosine_sim_matrix(embeddings_a, embeddings_b) -> np.array:
+    """
+    finds out cosine similarity matrix for the given embeddings
+    :param embeddings_a:
+    :param embeddings_b:
+    :return: numpy array showing the cosine similarity matrix
+    """
+    return np.array(
+        util.pytorch_cos_sim(embeddings_a, embeddings_b)
+    )

Functionalities/Streamlit_helpers.py

@@ -0,0 +1,83 @@
+import pandas as pd
+import streamlit as st
+from pandas.api.types import (
+    is_categorical_dtype,
+    is_datetime64_any_dtype,
+    is_numeric_dtype,
+    is_object_dtype,
+)
+
+
+def filter_dataframe(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Adds a UI on top of a dataframe to let viewers filter columns
+    Args:
+        df (pd.DataFrame): Original dataframe
+    Returns:
+        pd.DataFrame: Filtered dataframe
+    """
+    modify = st.checkbox("Add filters")
+
+    if not modify:
+        return df
+
+    df = df.copy()
+
+    # Try to convert datetimes into a standard format (datetime, no timezone)
+    for col in df.columns:
+        if is_object_dtype(df[col]):
+            try:
+                df[col] = pd.to_datetime(df[col])
+            except Exception:
+                pass
+
+        if is_datetime64_any_dtype(df[col]):
+            df[col] = df[col].dt.tz_localize(None)
+
+    modification_container = st.container()
+
+    with modification_container:
+        to_filter_columns = st.multiselect("Filter dataframe on", df.columns)
+        for column in to_filter_columns:
+            left, right = st.columns((1, 20))
+            left.write("↳")
+            # Treat columns with < 10 unique values as categorical
+            if is_categorical_dtype(df[column]) or df[column].nunique() < 10:
+                user_cat_input = right.multiselect(
+                    f"Values for {column}",
+                    df[column].unique(),
+                    default=list(df[column].unique()),
+                )
+                df = df[df[column].isin(user_cat_input)]
+            elif is_numeric_dtype(df[column]):
+                _min = float(df[column].min())
+                _max = float(df[column].max())
+                step = (_max - _min) / 100
+                user_num_input = right.slider(
+                    f"Values for {column}",
+                    _min,
+                    _max,
+                    (_min, _max),
+                    step=step,
+                )
+                df = df[df[column].between(*user_num_input)]
+            elif is_datetime64_any_dtype(df[column]):
+                user_date_input = right.date_input(
+                    f"Values for {column}",
+                    value=(
+                        df[column].min(),
+                        df[column].max(),
+                    ),
+                )
+                if len(user_date_input) == 2:
+                    user_date_input = tuple(map(pd.to_datetime, user_date_input))
+                    start_date, end_date = user_date_input
+                    df = df.loc[df[column].between(start_date, end_date)]
+            else:
+                user_text_input = right.text_input(
+                    f"Substring or regex in {column}",
+                )
+                if user_text_input:
+                    df = df[df[column].str.contains(user_text_input)]
+
+    return df

Functionalities/TopicClustering.py

@@ -0,0 +1,50 @@
+import pandas as pd
+from sentence_transformers import SentenceTransformer
+from bertopic import BERTopic
+from umap import UMAP
+from Functionalities import NLP_Helper
+# Visualization
+import plotly.graph_objects as go
+
+
+class TopicClustering:
+    def __init__(self, keyword_df, text_col, representation_model, sentence_model):
+        self.topic_model = None
+        self.embeddings = None
+        self.keyword_df, self.text_col = keyword_df, text_col
+        self.sentence_model = SentenceTransformer(sentence_model)
+        self.representation_model = NLP_Helper.get_bertopic_representation(representation_model)
+
+    def topic_cluster_bert(self) -> None:
+        self.embeddings = self.sentence_model.encode(self.keyword_df[self.text_col], show_progress_bar=False)
+        self.topic_model = BERTopic(representation_model=self.representation_model,
+                                    embedding_model=self.sentence_model,
+                                    n_gram_range=(1, 3), top_n_words=2)
+        topics, _ = self.topic_model.fit_transform(self.keyword_df[self.text_col])
+        topic_labels = self.topic_model.generate_topic_labels(nr_words=1, topic_prefix=False)
+
+        if self.topic_model.get_topic_info()['Topic'].values[0] == -1:
+            topic_labels[0] = 'Unknown'
+        self.topic_model.set_topic_labels(topic_labels)
+
+        self.keyword_df['Topic'] = topics
+        topic_info = self.topic_model.get_topic_info()
+
+        topic_info['Name'] = topic_labels
+        self.keyword_df = pd.merge(topic_info, self.keyword_df, on=['Topic'])
+        self.keyword_df.rename(columns={'Name': 'Topic Name'}, inplace=True)
+        self.keyword_df.drop(columns=['CustomName'], inplace=True)
+
+
+    def visualize_documents(self, n_neighbors) -> go.Figure:
+        reduced_embeddings = UMAP(n_neighbors=n_neighbors, n_components=2, min_dist=0.0, metric='cosine').fit_transform(
+            self.embeddings)
+
+        fig = self.topic_model.visualize_documents(self.keyword_df[self.text_col],
+                                                   reduced_embeddings=reduced_embeddings,
+                                                   custom_labels=True)
+        return fig
+
+    def visualize_topic_distribution(self) -> go.Figure:
+        fig = self.topic_model.visualize_barchart(custom_labels=True, top_n_topics=5, n_words=20, title='Topic Distribution')
+        return fig

LICENSE

@@ -0,0 +1,674 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.  We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors.  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights.  Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received.  You must make sure that they, too, receive
+or can get the source code.  And you must show them these terms so they
+know their rights.
+
+  Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+  For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software.  For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+  Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so.  This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software.  The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable.  Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products.  If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+  Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary.  To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Use with the GNU Affero General Public License.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+    <program>  Copyright (C) <year>  <name of author>
+    This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+<https://www.gnu.org/licenses/>.
+
+  The GNU General Public License does not permit incorporating your program
+into proprietary programs.  If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.  But first, please read
+<https://www.gnu.org/licenses/why-not-lgpl.html>.

README.md

@@ -1,12 +1,12 @@
----
-title: Google Ads Space
-emoji: 🌖
-colorFrom: blue
-colorTo: green
-sdk: streamlit
-sdk_version: 1.19.0
-app_file: app.py
-pinned: false
----
+# Google Ads Keyword Adgrouper
+Predicts Ad group for new keywords in google ads campaign.
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# How to Use
+
+# TODO
+- Handle exceptions
+- Write tests
+
+# Helper repositories 
+(Thanks for these resources!)
+- https://github.com/tylerjrichards/st-filter-dataframe

app.py

@@ -0,0 +1,11 @@
+import streamlit as st
+from streamlit_extras.switch_page_button import switch_page
+
+st.set_page_config(page_title='Google Ads NLP Tasks', layout="wide")
+st.markdown("## Google Ads Tasks")
+new_kw_grouper_btn = st.button("New Keyword Ad grouper")
+topic_clustering_btn = st.button("Topic Clustering")
+if new_kw_grouper_btn:
+    switch_page("New Keyword Ad grouper")
+elif topic_clustering_btn:
+    switch_page("Topic Cluster")

pages/1_New Keyword Ad grouper.py

@@ -0,0 +1,105 @@
+import pandas as pd
+import streamlit as st
+
+from Functionalities.Streamlit_helpers import filter_dataframe
+from Functionalities.KeywordAdgroupPredict import KeywordAdgroupPredict
+
+
+class NewKeywordAdGrouper:
+
+    def __init__(self):
+        self.new_kw_df = None
+        self.cur_kw_df = None
+        self.selected_features = None
+        self.features = None
+        self.cur_kw_file_camp_col = None
+        self.cur_kw_file_adg_col = None
+        self.new_kw_file = None
+        self.cur_kw_file = None
+        self.new_kw_file_kw_col = None
+        self.cur_kw_file_kw_col = None
+        st.session_state.predict_df = pd.DataFrame() \
+            if 'predict_df' not in st.session_state else st.session_state.predict_df
+
+        st.set_page_config(page_title='Google Ads Keyword Ad grouper', layout="wide")
+        st.header("Google Ads Keyword Ad grouper")
+        st.write(f"This page tries to predict the suitable ad group for new keywords "
+                 f"based on the keywords already existing in the campaign.")
+        st.write(f"Please make sure you DON'T have the following column names in the New Keyword CSV\n"
+                 f"1. Recommended Ad group\n2. relevance score")
+
+    def input_file_features(self) -> None:
+        """
+        Takes 2 file inputs, 1 feature input using checkboxes, 1 button for running prediction
+        :return:
+        """
+        self.new_kw_file = st.file_uploader(label="Upload the CSV file containing the new keywords")
+
+        if self.new_kw_file:
+            self.new_kw_df = pd.read_csv(self.new_kw_file)
+            if 'Recommended Ad group' in self.new_kw_df.columns or 'relevance score' in self.new_kw_df.columns:
+                st.error(f"Please make sure you DON'T have the following column names in the New Keyword CSV\n"
+                         f"1. Recommended Ad group\n2. relevance score")
+            self.new_kw_file_kw_col = st.selectbox(
+                label=f"Select the Keyword Column in **{self.new_kw_file.name}**", options=self.new_kw_df.columns
+            )
+
+        self.cur_kw_file = st.file_uploader(label="Upload the CSV file containing the current keywords, "
+                                                  "their ad group, and campaign (Search keyword report)")
+
+        if self.cur_kw_file:
+            self.cur_kw_df = pd.read_csv(self.cur_kw_file)
+            self.cur_kw_file_kw_col = st.selectbox(label=f"Select the Keyword Column in **{self.cur_kw_file.name}**",
+                                                   options=self.cur_kw_df.columns, index=0)
+            self.cur_kw_file_adg_col = st.selectbox(label=f"Select Ad Group Column in **{self.cur_kw_file.name}**",
+                                                    options=self.cur_kw_df.columns, index=3)
+            self.cur_kw_file_camp_col = st.selectbox(label=f"Select Campaign Column in **{self.cur_kw_file.name}**",
+                                                     options=self.cur_kw_df.columns, index=2)
+
+        if self.new_kw_file and self.cur_kw_file:
+            self.features = {self.cur_kw_file_kw_col: False, self.cur_kw_file_adg_col: False}
+            st.write('Select the features you want to use for finding relevant ad group for new keywords:')
+            self.features[self.cur_kw_file_kw_col] = st.checkbox('Ad group Keywords', value=True)
+            self.features[self.cur_kw_file_adg_col] = st.checkbox('Ad group name')
+
+            self.selected_features = [key for key, value in self.features.items() if value == True]
+
+            st.button("Predict", on_click=self.run_prediction)
+        else:
+            st.info("Please upload necessary files")
+
+    def run_prediction(self) -> None:
+        """
+        runs ad group prediction for given inputs on button press
+        :return:
+        """
+        if not (self.features[self.cur_kw_file_kw_col] or self.features[self.cur_kw_file_adg_col]):
+            st.error("Please select at least one feature")
+        else:
+            kw_adg_predict = KeywordAdgroupPredict()
+            st.session_state.predict_df = kw_adg_predict.predict_ad_group_for_keywords(
+                candidate_kw_df=self.new_kw_df, cur_kw_df=self.cur_kw_df, features=self.selected_features,
+                new_kw_col=self.new_kw_file_kw_col, cur_kw_col=self.cur_kw_file_kw_col,
+                cur_adg_col=self.cur_kw_file_adg_col, cur_camp_col=self.cur_kw_file_camp_col)
+
+    def output(self) -> None:
+        """
+        Outputs the dataframe containing ad group prediction and relevance score
+        :return:
+        """
+        if not st.session_state.predict_df.empty:
+            filtered_df = filter_dataframe(st.session_state.predict_df)
+            st.dataframe(filtered_df)
+            st.download_button(
+                "Press to Download",
+                filtered_df.to_csv(index=False).encode('utf-8'),
+                "Keyword Ad group Prediction.csv",
+                "text/csv",
+                key='download-csv'
+            )
+
+
+if __name__ == '__main__':
+    new_kw_ad_grouper = NewKeywordAdGrouper()
+    new_kw_ad_grouper.input_file_features()
+    new_kw_ad_grouper.output()

pages/2_Topic_Cluster.py

@@ -0,0 +1,98 @@
+import pandas as pd
+import streamlit as st
+from Functionalities import NLP_Helper
+from Functionalities.TopicClustering import TopicClustering
+from streamlit_extras.dataframe_explorer import dataframe_explorer
+
+class TopicClusterView:
+    def __init__(self):
+        self.n_neighbors = 10
+        self.topic_cluster = None
+        self.representation_model = None
+        self.sentence_model = None
+        self.text_col = None
+        self.text_df = None
+        self.text_file = None
+
+        st.session_state.topic_cluster = None \
+            if 'topic_cluster' not in st.session_state else st.session_state.topic_cluster
+
+        st.set_page_config(page_title='Topic Clustering', layout="wide")
+        st.header("Topic Clustering")
+        # st.write(f"This page tries to predict the suitable ad group for new keywords "
+        #          f"based on the keywords already existing in the campaign.")
+
+    def input_params(self) -> None:
+        """
+        Takes csv file input, name of text col, select option for sentence model and representation model
+        :return:
+        """
+        self.text_file = st.file_uploader(label="Upload the CSV file containing the texts to cluster")
+        if self.text_file:
+            self.text_df = pd.read_csv(self.text_file)
+            self.text_col = st.selectbox(
+                label=f"Choose the column to use for topic clustering in **{self.text_file.name}**",
+                options=self.text_df.columns
+            )
+
+            self.sentence_model = st.selectbox(
+                label=f"Choose the text embedding model",
+                options=NLP_Helper.TRANSFORMERS,
+                help="; ".join(NLP_Helper.TRANSFORMERS_INFO)
+            )
+
+            self.representation_model = st.selectbox(
+                label=f"Choose the representation model",
+                options=NLP_Helper.BERTOPIC_REPRESENTATIONS,
+            )
+
+            st.button("Cluster", on_click=self.run_clustering)
+
+    def run_clustering(self) -> None:
+        self.topic_cluster = TopicClustering(keyword_df=self.text_df, text_col=self.text_col,
+                                             representation_model=self.representation_model,
+                                             sentence_model=self.sentence_model)
+
+        self.topic_cluster.topic_cluster_bert()
+        st.session_state.topic_cluster = self.topic_cluster
+
+    def show_and_download_df(self):
+        if (st.session_state.topic_cluster is not None) and (st.session_state.topic_cluster.topic_model is not None):
+            filtered_df = dataframe_explorer(st.session_state.topic_cluster.keyword_df)
+            st.dataframe(filtered_df)
+            st.download_button(
+                "Press to Download",
+                st.session_state.topic_cluster.keyword_df.to_csv(index=False).encode('utf-8'),
+                "Clustered.csv",
+                "text/csv",
+                key='download-csv'
+            )
+
+    def visualize_clusters(self):
+        if (st.session_state.topic_cluster is not None) and (st.session_state.topic_cluster.topic_model is not None):
+            self.n_neighbors = st.slider(label='Size of the local neighborhood', min_value=2, max_value=100, step=1)
+            if st.button("Visualize Topic Clusters"):
+                if (st.session_state.topic_cluster is not None) and (
+                        st.session_state.topic_cluster.topic_model is not None):
+                    fig = st.session_state.topic_cluster.visualize_documents(n_neighbors=self.n_neighbors)
+                    fig.update_layout(title=None)
+                    st.plotly_chart(fig, use_container_width=True, theme=None)
+
+    def visualize_topic_distribution(self):
+        if (st.session_state.topic_cluster is not None) and (st.session_state.topic_cluster.topic_model is not None):
+            if (st.session_state.topic_cluster is not None) and (
+                    st.session_state.topic_cluster.topic_model is not None):
+                fig = st.session_state.topic_cluster.visualize_topic_distribution()
+                st.plotly_chart(fig, use_container_width=True, theme=None)
+
+if __name__ == '__main__':
+    topic_cluster_view = TopicClusterView()
+    # tab1, tab2, tab3 = st.tabs(['Clustering Process', 'Cluster Visualization', 'Topic Distribution'])
+    tab1, tab2 = st.tabs(['Clustering Process', 'Cluster Visualization'])
+    with tab1:
+        topic_cluster_view.input_params()
+        topic_cluster_view.show_and_download_df()
+    with tab2:
+        topic_cluster_view.visualize_clusters()
+    # with tab3:
+    #     topic_cluster_view.visualize_topic_distribution()

requirements.txt

@@ -0,0 +1,103 @@
+accelerate==0.18.0
+altair==4.2.2
+attrs==22.2.0
+beautifulsoup4==4.12.0
+bertopic==0.14.1
+blinker==1.5
+cachetools==5.3.0
+certifi==2022.12.7
+charset-normalizer==3.1.0
+click==8.1.3
+contourpy==1.0.7
+cycler==0.11.0
+Cython==0.29.34
+decorator==5.1.1
+entrypoints==0.4
+Faker==18.3.1
+favicon==0.7.0
+filelock==3.10.7
+fonttools==4.39.3
+gitdb==4.0.10
+GitPython==3.1.31
+hdbscan==0.8.29
+htbuilder==0.6.1
+huggingface-hub==0.13.3
+idna==3.4
+importlib-metadata==6.1.0
+install==1.3.5
+Jinja2==3.1.2
+joblib==1.2.0
+jsonschema==4.17.3
+kiwisolver==1.4.4
+llvmlite==0.39.1
+lxml==4.9.2
+Markdown==3.4.3
+markdown-it-py==2.2.0
+markdownlit==0.0.5
+MarkupSafe==2.1.2
+matplotlib==3.7.1
+mdurl==0.1.2
+more-itertools==9.1.0
+mpmath==1.3.0
+networkx==3.0
+nltk==3.8.1
+numba==0.56.4
+numpy==1.23.5
+packaging==23.0
+pandas==1.5.3
+Pillow==9.4.0
+plotly==5.14.1
+protobuf==3.20.3
+psutil==5.9.5
+pyarrow==11.0.0
+pydeck==0.8.0
+Pygments==2.14.0
+pymdown-extensions==9.10
+Pympler==1.0.1
+pynndescent==0.5.9
+pyparsing==3.0.9
+pyrsistent==0.19.3
+python-dateutil==2.8.2
+pytz==2023.3
+pytz-deprecation-shim==0.1.0.post0
+PyYAML==6.0
+regex==2023.3.23
+requests==2.28.2
+rich==13.3.3
+scikit-learn==1.2.2
+scipy==1.10.1
+semver==2.13.0
+sentence-transformers==2.2.2
+sentencepiece==0.1.97
+six==1.16.0
+smmap==5.0.0
+soupsieve==2.4
+st-annotated-text==3.0.0
+streamlit==1.20.0
+streamlit-camera-input-live==0.2.0
+streamlit-card==0.0.4
+streamlit-embedcode==0.1.2
+streamlit-extras==0.2.6
+streamlit-faker==0.0.2
+streamlit-image-coordinates==0.1.3
+streamlit-keyup==0.2.0
+streamlit-toggle-switch==1.0.2
+streamlit-vertical-slider==1.0.2
+sympy==1.11.1
+tenacity==8.2.2
+threadpoolctl==3.1.0
+tokenizers==0.13.2
+toml==0.10.2
+toolz==0.12.0
+torch==2.0.0
+torchvision==0.15.1
+tornado==6.2
+tqdm==4.65.0
+transformers==4.25.1
+typing_extensions==4.5.0
+tzdata==2023.3
+tzlocal==4.3
+umap-learn==0.5.3
+urllib3==1.26.15
+validators==0.20.0
+zipp==3.15.0