🙈

.pylintrc

@@ -0,0 +1,333 @@
+[MASTER]
+
+# Specify a configuration file.
+#rcfile=
+
+# Python code to execute, usually for sys.path manipulation such as
+# pygtk.require().
+#init-hook=
+
+# Profiled execution.
+profile=no
+
+# Add files or directories to the blacklist. They should be base names, not
+# paths.
+ignore=CVS
+
+# Pickle collected data for later comparisons.
+persistent=yes
+
+# List of plugins (as comma separated values of python modules names) to load,
+# usually to register additional checkers.
+load-plugins=
+
+
+[MESSAGES CONTROL]
+
+# Enable the message, report, category or checker with the given id(s). You can
+# either give multiple identifier separated by comma (,) or put this option
+# multiple time. See also the "--disable" option for examples.
+enable=indexing-exception,old-raise-syntax
+
+# Disable the message, report, category or checker with the given id(s). You
+# can either give multiple identifiers separated by comma (,) or put this
+# option multiple times (only on the command line, not in the configuration
+# file where it should appear only once).You can also use "--disable=all" to
+# disable everything first and then reenable specific checks. For example, if
+# you want to run only the similarities checker, you can use "--disable=all
+# --enable=similarities". If you want to run only the classes checker, but have
+# no Warning level messages displayed, use"--disable=all --enable=classes
+# --disable=W"
+disable=design,similarities,no-self-use,attribute-defined-outside-init,locally-disabled,star-args,pointless-except,bad-option-value,global-statement,fixme,suppressed-message,useless-suppression,locally-enabled,no-member,no-name-in-module,import-error,unsubscriptable-object,unbalanced-tuple-unpacking,undefined-variable,not-context-manager,no-else-return,wrong-import-order,unnecessary-pass,logging-fstring-interpolation,logging-format-interpolation,C0330,C0114
+
+
+# Set the cache size for astng objects.
+cache-size=500
+
+
+[REPORTS]
+
+# Set the output format. Available formats are text, parseable, colorized, msvs
+# (visual studio) and html. You can also give a reporter class, eg
+# mypackage.mymodule.MyReporterClass.
+output-format=text
+
+# Put messages in a separate file for each module / package specified on the
+# command line instead of printing them on stdout. Reports (if any) will be
+# written in a file name "pylint_global.[txt|html]".
+files-output=no
+
+# Tells whether to display a full report or only the messages
+reports=no
+
+# Python expression which should return a note less than 10 (10 is the highest
+# note). You have access to the variables errors warning, statement which
+# respectively contain the number of errors / warnings messages and the total
+# number of statements analyzed. This is used by the global evaluation report
+# (RP0004).
+evaluation=10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10)
+
+# Add a comment according to your evaluation note. This is used by the global
+# evaluation report (RP0004).
+comment=no
+
+# Template used to display messages. This is a python new-style format string
+# used to format the message information. See doc for all details
+#msg-template=
+
+
+[TYPECHECK]
+
+# Tells whether missing members accessed in mixin class should be ignored. A
+# mixin class is detected if its name ends with "mixin" (case insensitive).
+ignore-mixin-members=yes
+
+# List of classes names for which member attributes should not be checked
+# (useful for classes with attributes dynamically set).
+ignored-classes=SQLObject
+
+# When zope mode is activated, add a predefined set of Zope acquired attributes
+# to generated-members.
+zope=no
+
+# List of members which are set dynamically and missed by pylint inference
+# system, and so shouldn't trigger E0201 when accessed. Python regular
+# expressions are accepted.
+generated-members=REQUEST,acl_users,aq_parent
+
+# List of decorators that create context managers from functions, such as
+# contextlib.contextmanager.
+contextmanager-decorators=contextlib.contextmanager,contextlib2.contextmanager
+
+
+[VARIABLES]
+
+# Tells whether we should check for unused import in __init__ files.
+init-import=no
+
+# A regular expression matching the beginning of the name of dummy variables
+# (i.e. not used).
+dummy-variables-rgx=^\*{0,2}(_$|unused_|dummy_)
+
+# List of additional names supposed to be defined in builtins. Remember that
+# you should avoid to define new builtins when possible.
+additional-builtins=
+
+
+[BASIC]
+
+# Required attributes for module, separated by a comma
+required-attributes=
+
+# List of builtins function names that should not be used, separated by a comma
+bad-functions=apply,input,reduce
+
+
+# Disable the report(s) with the given id(s).
+# All non-Google reports are disabled by default.
+disable-report=R0001,R0002,R0003,R0004,R0101,R0102,R0201,R0202,R0220,R0401,R0402,R0701,R0801,R0901,R0902,R0903,R0904,R0911,R0912,R0913,R0914,R0915,R0921,R0922,R0923
+
+# Regular expression which should only match correct module names
+module-rgx=(([a-z_][a-z0-9_]*)|([A-Z][a-zA-Z0-9]+))$
+
+# Regular expression which should only match correct module level names
+const-rgx=^(_?[A-Z][A-Z0-9_]*|__[a-z0-9_]+__|_?[a-z][a-z0-9_]*)$
+
+# Regular expression which should only match correct class names
+class-rgx=^_?[A-Z][a-zA-Z0-9]*$
+
+# Regular expression which should only match correct function names
+function-rgx=^(?:(?P<camel_case>_?[A-Z][a-zA-Z0-9]*)|(?P<snake_case>_?[a-z][a-z0-9_]*))$
+
+# Regular expression which should only match correct method names
+method-rgx=^(?:(?P<exempt>__[a-z0-9_]+__|next)|(?P<camel_case>_{0,2}[A-Z][a-zA-Z0-9]*)|(?P<snake_case>_{0,2}[a-z][a-z0-9_]*))$
+
+# Regular expression which should only match correct instance attribute names
+attr-rgx=^_{0,2}[a-z][a-z0-9_]*$
+
+# Regular expression which should only match correct argument names
+argument-rgx=^[a-z][a-z0-9_]*$
+
+# Regular expression which should only match correct variable names
+variable-rgx=^[a-z][a-z0-9_]*$
+
+# Regular expression which should only match correct attribute names in class
+# bodies
+class-attribute-rgx=^(_?[A-Z][A-Z0-9_]*|__[a-z0-9_]+__|_?[a-z][a-z0-9_]*)$
+
+# Regular expression which should only match correct list comprehension /
+# generator expression variable names
+inlinevar-rgx=^[a-z][a-z0-9_]*$
+
+# Good variable names which should always be accepted, separated by a comma
+good-names=main,_
+
+# Bad variable names which should always be refused, separated by a comma
+bad-names=
+
+# Regular expression which should only match function or class names that do
+# not require a docstring.
+no-docstring-rgx=(__.*__|main)
+
+# Minimum line length for functions/classes that require docstrings, shorter
+# ones are exempt.
+docstring-min-length=10
+
+
+[FORMAT]
+
+# Maximum number of characters on a single line.
+max-line-length=120
+
+# Regexp for a line that is allowed to be longer than the limit.
+ignore-long-lines=(?x)
+  (^\s*(import|from)\s
+   |\$Id:\s\/\/depot\/.+#\d+\s\$
+   |^[a-zA-Z_][a-zA-Z0-9_]*\s*=\s*("[^"]\S+"|'[^']\S+')
+   |^\s*\#\ LINT\.ThenChange
+   |^[^#]*\#\ type:\ [a-zA-Z_][a-zA-Z0-9_.,[\] ]*$
+   |pylint
+   |"""
+   |\#
+   |lambda
+   |(https?|ftp):)
+
+# Allow the body of an if to be on the same line as the test if there is no
+# else.
+single-line-if-stmt=y
+
+# List of optional constructs for which whitespace checking is disabled
+no-space-check=
+
+# Maximum number of lines in a module
+max-module-lines=99999
+
+# String used as indentation unit. This is usually " " (4 spaces) or "\t" (1
+# tab).
+indent-string='    '
+
+# Set the linting for string quotes
+string-quote=single
+triple-quote=double
+docstring-quote=double
+
+[SIMILARITIES]
+
+# Minimum lines number of a similarity.
+min-similarity-lines=4
+
+# Ignore comments when computing similarities.
+ignore-comments=yes
+
+# Ignore docstrings when computing similarities.
+ignore-docstrings=yes
+
+# Ignore imports when computing similarities.
+ignore-imports=no
+
+
+[MISCELLANEOUS]
+
+# List of note tags to take in consideration, separated by a comma.
+notes=
+
+
+[IMPORTS]
+
+# Deprecated modules which should not be used, separated by a comma
+deprecated-modules=regsub,TERMIOS,Bastion,rexec,sets
+
+# Create a graph of every (i.e. internal and external) dependencies in the
+# given file (report RP0402 must not be disabled)
+import-graph=
+
+# Create a graph of external dependencies in the given file (report RP0402 must
+# not be disabled)
+ext-import-graph=
+
+# Create a graph of internal dependencies in the given file (report RP0402 must
+# not be disabled)
+int-import-graph=
+
+extension-pkg-whitelist=_jsonnet
+
+
+[CLASSES]
+
+# List of interface methods to ignore, separated by a comma. This is used for
+# instance to not check methods defines in Zope's Interface base class.
+ignore-iface-methods=isImplementedBy,deferred,extends,names,namesAndDescriptions,queryDescriptionFor,getBases,getDescriptionFor,getDoc,getName,getTaggedValue,getTaggedValueTags,isEqualOrExtendedBy,setTaggedValue,isImplementedByInstancesOf,adaptWith,is_implemented_by
+
+# List of method names used to declare (i.e. assign) instance attributes.
+defining-attr-methods=__init__,__new__,setUp
+
+# List of valid names for the first argument in a class method.
+valid-classmethod-first-arg=cls,class_
+
+# List of valid names for the first argument in a metaclass class method.
+valid-metaclass-classmethod-first-arg=mcs
+
+
+[DESIGN]
+
+# Maximum number of arguments for function / method
+max-args=5
+
+# Argument names that match this expression will be ignored. Default to name
+# with leading underscore
+ignored-argument-names=_.*
+
+# Maximum number of locals for function / method body
+max-locals=15
+
+# Maximum number of return / yield for function / method body
+max-returns=6
+
+# Maximum number of branch for function / method body
+max-branches=12
+
+# Maximum number of statements in function / method body
+max-statements=50
+
+# Maximum number of parents for a class (see R0901).
+max-parents=7
+
+# Maximum number of attributes for a class (see R0902).
+max-attributes=7
+
+# Minimum number of public methods for a class (see R0903).
+min-public-methods=2
+
+# Maximum number of public methods for a class (see R0904).
+max-public-methods=20
+
+
+[EXCEPTIONS]
+
+# Exceptions that will emit a warning when being caught. Defaults to
+# "Exception"
+overgeneral-exceptions=Exception,StandardError,BaseException
+
+
+[AST]
+
+# Maximum line length for lambdas
+short-func-length=1
+
+# List of module members that should be marked as deprecated.
+# All of the string functions are listed in 4.1.4 Deprecated string functions
+# in the Python 2.4 docs.
+deprecated-members=string.atof,string.atoi,string.atol,string.capitalize,string.expandtabs,string.find,string.rfind,string.index,string.rindex,string.count,string.lower,string.split,string.rsplit,string.splitfields,string.join,string.joinfields,string.lstrip,string.rstrip,string.strip,string.swapcase,string.translate,string.upper,string.ljust,string.rjust,string.center,string.zfill,string.replace,sys.exitfunc
+
+
+[DOCSTRING]
+
+# List of exceptions that do not need to be mentioned in the Raises section of
+# a docstring.
+ignore-exceptions=AssertionError,NotImplementedError,StopIteration,TypeError
+
+[TOKENS]
+
+# Number of spaces of indent required when the last token on the preceding line
+# is an open (, [, or {.
+indent-after-paren=4

Makefile

@@ -0,0 +1,15 @@
+push:
+	git add .
+	git commit -m "🙈"
+	git push
+
+
+install: ## [DEVELOPMENT] Install the API dependencies
+	virtualenv env; \
+	source env/bin/activate; \
+	pip install -r requirements.txt; \
+	pip install -r requirements-test.txt
+	@echo "Done, run '\033[0;31msource env/bin/activate\033[0m' to activate the virtual environment"
+
+run: ## [DEVELOPMENT] Run the streamlit app
+	streamlit run app.py

app.py

@@ -0,0 +1,107 @@
+import streamlit as st
+from datasets import load_dataset
+import pandas as pd
+
+
+dataset = load_dataset("Langame/starter2")
+
+conversation_starters = []
+for i in range(len(dataset["train"])):
+    conversation_starters.append({
+        "conversation_starter": dataset["train"][i]["content"],
+        "topics": dataset["train"][i]["topics"]
+    })
+
+df = pd.DataFrame(conversation_starters)
+
+from pandas.api.types import (
+    is_categorical_dtype,
+    is_datetime64_any_dtype,
+    is_numeric_dtype,
+    is_object_dtype,
+)
+
+st.title("Conversation starters")
+
+st.write(
+    """Quick hack to search conversation starters for your next conversations in https://huggingface.co/datasets/Langame/starter2
+    """
+)
+
+
+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
+
+
+st.dataframe(filter_dataframe(df))

requirements-test.txt

@@ -0,0 +1,12 @@
+black
+mypy
+pylint
+pytest-cov
+pytest-xdist
+pytest
+ipykernel
+ipywidgets
+httpx
+trio
+pytest-asyncio
+watchdog

requirements.txt

@@ -0,0 +1,3 @@
+pandas
+datasets
+streamlit