Merge pull request #49 from lucasrodes/release/0.2.6

Release/0.2.6

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.2.5
+current_version = 0.2.6
 
 [bumpversion:file:setup.py]
 

README.md

@@ -1,8 +1,8 @@
 # whatstk: python whatsapp parser and analysis tool
 
-![Package version](https://img.shields.io/badge/whatstk-v0.2.5-teal.svg?style=for-the-badge&color=25D366&logo=whatsapp)
+![Package version](https://img.shields.io/badge/whatstk-v0.2.6-teal.svg?style=for-the-badge&color=25D366&logo=whatsapp)
 
-[![Build Status](https://travis-ci.com/lucasrodes/whatstk.svg?branch=develop)](https://travis-ci.com/lucasrodes/whatstk)
+[![Build Status](https://travis-ci.com/lucasrodes/whatstk.svg?branch=develop)](https://travis-ci.org/lucasrodes/whatstk)
 [![codecov](https://codecov.io/gh/lucasrodes/whatstk/branch/master/graph/badge.svg)](https://codecov.io/gh/lucasrodes/whatstk)
 [![Python 3.6](https://img.shields.io/badge/python-3.7|3.8-blue.svg)](https://www.python.org/downloads/release/python-3/)
 [![Documentation](https://img.shields.io/badge/documentation-royalblue.svg)](docs/index.md)
@@ -162,15 +162,10 @@ header unit.
 
 ---
 
-## Known issues
-- 12h clock header format is not supported.
-
----
-
 ## Contributing
 
 We are very open to have collaborators. You can freely fork and issue a pull request with your updates!
-For other issues/bugs/suggestions, please report it as an issue or [text me](mailto:[email protected]).
+For other issues/bugs/suggestions, please report it in the [issues section](https://github.com/lucasrodes/whatstk/issues).
 
 ### Pull Requests
 

setup.py

@@ -12,7 +12,7 @@
 
 setup(
  name='whatstk',
- version="0.2.5",
+ version="0.2.6",
  description="Parser and analytics tools for WhatsApp group chats",
  long_description=long_description,
  long_description_content_type='text/markdown',

tests/chats/example-12h-2.txt

@@ -0,0 +1,20 @@
+2016-04-15, 3:04 p.m. - You created group “Sample Group”
+2016-08-06, 1:18 p.m. - Messages you send to this group are now secured with end-to-end encryption. Tap for more info.
+2016-08-06, 1:23 p.m. - Ash Ketchum: Hey guys!
+2016-08-06, 1:25 p.m. - Brock: Hey Ash, good to have a common group!
+2016-08-06, 1:30 p.m. - Misty: Hey guys! Long time haven't heard anything from you
+2016-08-06, 1:45 p.m. - Ash Ketchum: Indeed. I think having a whatsapp group nowadays is a good idea
+2016-08-06, 2:30 p.m. - Misty: Definetly
+2016-08-06, 5:25 p.m. - Brock: I totally agree
+2016-08-07, 11:45 p.m. - Prof. Oak: Kids, shall I design a smart poke-ball?
+2016-08-07, 6:45 p.m. - Ash Ketchum: I don't mind Prof. I quitted capturing pokemon.
+2016-08-07, 7:30 p.m. - Misty: Was a great time, but had enough also.
+2016-08-07, 11:25 p.m. - Brock: Guys, I am still in the first gym. No one is playing pokemon, they went crazy with pokemon Go.
+2016-08-10, 09:45 p.m. - Jessie & James: Hey, thanks for adding us. Wanna meet soon? Just for the old times.
+2016-08-10, 11:25 p.m. - Raichu: I am in!
+2016-08-10, 1:23 p.m. - Ash Ketchum: FFS, no way, Pikachu did you evolve?
+2016-08-10, 3:23 p.m. - Raichu: Yes... Weird to have a different body!
+2016-08-11, 7:30 p.m. - Misty: Gotta see that.
+2016-09-11, 8:25 p.m. - Meowth: Hey people, I was on holidays in Sinnoh. Crazy region.
+2016-10-31, 11:45 p.m. - Prof. Oak: Smart-pokeball is created.
+2016-10-31, 02:23 p.m. - Wobbuffet: Wo-bbu-ffet

tests/chats/example-12h.txt

@@ -0,0 +1,20 @@
+2016-04-15, 3:04 PM - You created group “Sample Group”
+2016-08-06, 1:18 PM - Messages you send to this group are now secured with end-to-end encryption. Tap for more info.
+2016-08-06, 1:23 PM - Ash Ketchum: Hey guys!
+2016-08-06, 1:25 PM - Brock: Hey Ash, good to have a common group!
+2016-08-06, 1:30 PM - Misty: Hey guys! Long time haven't heard anything from you
+2016-08-06, 1:45 PM - Ash Ketchum: Indeed. I think having a whatsapp group nowadays is a good idea
+2016-08-06, 2:30 PM - Misty: Definetly
+2016-08-06, 5:25 PM - Brock: I totally agree
+2016-08-07, 11:45 PM - Prof. Oak: Kids, shall I design a smart poke-ball?
+2016-08-07, 6:45 PM - Ash Ketchum: I don't mind Prof. I quitted capturing pokemon.
+2016-08-07, 7:30 PM - Misty: Was a great time, but had enough also.
+2016-08-07, 11:25 PM - Brock: Guys, I am still in the first gym. No one is playing pokemon, they went crazy with pokemon Go.
+2016-08-10, 09:45 AM - Jessie & James: Hey, thanks for adding us. Wanna meet soon? Just for the old times.
+2016-08-10, 11:25 AM - Raichu: I am in!
+2016-08-10, 1:23 PM - Ash Ketchum: FFS, no way, Pikachu did you evolve?
+2016-08-10, 3:23 PM - Raichu: Yes... Weird to have a different body!
+2016-08-11, 7:30 PM - Misty: Gotta see that.
+2016-09-11, 8:25 PM - Meowth: Hey people, I was on holidays in Sinnoh. Crazy region.
+2016-10-31, 11:45 PM - Prof. Oak: Smart-pokeball is created.
+2016-10-31, 02:23 PM - Wobbuffet: Wo-bbu-ffet

tests/test_analysis.py

@@ -2,174 +2,179 @@
 from whatstk.objects import WhatsAppChat
 import pandas as pd
 import pytest
+import os
+
+
+filenames_path = "./tests/chats"
+filenames = [os.path.join(filenames_path, f) for f in os.listdir(filenames_path) if f.endswith(".txt")]
 
 
 def test_interventions_date():
 
- filename = 'tests/chats/example_1.txt'
- chat = WhatsAppChat.from_txt(filename)
- counts = interventions(chat, date_mode='date', msg_length=False)
+ for filename in filenames:
+  chat = WhatsAppChat.from_txt(filename)
+  counts = interventions(chat, date_mode='date', msg_length=False)
 
- assert(isinstance(counts, pd.DataFrame))
- # Asswert chat df and counts df have same users
- assert(set(chat.users) == set(counts.columns))
+  assert(isinstance(counts, pd.DataFrame))
+  # Asswert chat df and counts df have same users
+  assert(set(chat.users) == set(counts.columns))
 
- # Assert chat df and counts df have same date window
- assert(chat.df.index.max().date() == counts.index.max().date())
- assert(chat.df.index.min().date() == counts.index.min().date())
+  # Assert chat df and counts df have same date window
+  assert(chat.df.index.max().date() == counts.index.max().date())
+  assert(chat.df.index.min().date() == counts.index.min().date())
 
 
 def test_interventions_date_msg_length():
 
- filename = 'tests/chats/example_1.txt'
- chat = WhatsAppChat.from_txt(filename)
- counts = interventions(chat, date_mode='date', msg_length=True)
+ for filename in filenames:
+  chat = WhatsAppChat.from_txt(filename)
+  counts = interventions(chat, date_mode='date', msg_length=True)
 
- assert(isinstance(counts, pd.DataFrame))
- # Asswert chat df and counts df have same users
- assert(set(chat.users) == set(counts.columns))
+  assert(isinstance(counts, pd.DataFrame))
+  # Asswert chat df and counts df have same users
+  assert(set(chat.users) == set(counts.columns))
 
- # Assert chat df and counts df have same date window
- assert(chat.df.index.max().date() == counts.index.max().date())
- assert(chat.df.index.min().date() == counts.index.min().date())
+  # Assert chat df and counts df have same date window
+  assert(chat.df.index.max().date() == counts.index.max().date())
+  assert(chat.df.index.min().date() == counts.index.min().date())
 
 
 def test_interventions_hour():
 
- filename = 'tests/chats/example_1.txt'
- chat = WhatsAppChat.from_txt(filename)
- counts = interventions(chat, date_mode='hour', msg_length=False)
+ for filename in filenames:
+  chat = WhatsAppChat.from_txt(filename)
+  counts = interventions(chat, date_mode='hour', msg_length=False)
 
- assert(isinstance(counts, pd.DataFrame))
- # Asswert chat df and counts df have same users
- assert(set(chat.users) == set(counts.columns))
+  assert(isinstance(counts, pd.DataFrame))
+  # Asswert chat df and counts df have same users
+  assert(set(chat.users) == set(counts.columns))
 
- # Check range hours
- assert(counts.index.max() == chat.df.index.hour.max())
- assert(counts.index.min() == chat.df.index.hour.min())
+  # Check range hours
+  assert(counts.index.max() == chat.df.index.hour.max())
+  assert(counts.index.min() == chat.df.index.hour.min())
 
 
 
 def test_interventions_hour_msg_length():
 
- filename = 'tests/chats/example_1.txt'
- chat = WhatsAppChat.from_txt(filename)
- counts = interventions(chat, date_mode='hour', msg_length=True)
+ for filename in filenames:
+  chat = WhatsAppChat.from_txt(filename)
+  counts = interventions(chat, date_mode='hour', msg_length=True)
 
- assert(isinstance(counts, pd.DataFrame))
- # Asswert chat df and counts df have same users
- assert(set(chat.users) == set(counts.columns))
+  assert(isinstance(counts, pd.DataFrame))
+  # Asswert chat df and counts df have same users
+  assert(set(chat.users) == set(counts.columns))
 
- # Check range hours
- assert(counts.index.max() == chat.df.index.hour.max())
- assert(counts.index.min() == chat.df.index.hour.min())
+  # Check range hours
+  assert(counts.index.max() == chat.df.index.hour.max())
+  assert(counts.index.min() == chat.df.index.hour.min())
 
 
 def test_interventions_month():
 
- filename = 'tests/chats/example_1.txt'
- chat = WhatsAppChat.from_txt(filename)
- counts = interventions(chat, date_mode='month', msg_length=False)
+ for filename in filenames:
+  chat = WhatsAppChat.from_txt(filename)
+  counts = interventions(chat, date_mode='month', msg_length=False)
 
- assert(isinstance(counts, pd.DataFrame))
- # Asswert chat df and counts df have same users
- assert(set(chat.users) == set(counts.columns))
+  assert(isinstance(counts, pd.DataFrame))
+  # Asswert chat df and counts df have same users
+  assert(set(chat.users) == set(counts.columns))
 
- # Check range hours
- assert(counts.index.max() == chat.df.index.month.max())
- assert(counts.index.min() == chat.df.index.month.min())
+  # Check range hours
+  assert(counts.index.max() == chat.df.index.month.max())
+  assert(counts.index.min() == chat.df.index.month.min())
 
 
 
 def test_interventions_month_msg_length():
 
- filename = 'tests/chats/example_1.txt'
- chat = WhatsAppChat.from_txt(filename)
- counts = interventions(chat, date_mode='month', msg_length=False)
+ for filename in filenames:
+  chat = WhatsAppChat.from_txt(filename)
+  counts = interventions(chat, date_mode='month', msg_length=False)
 
- assert(isinstance(counts, pd.DataFrame))
- # Asswert chat df and counts df have same users
- assert(set(chat.users) == set(counts.columns))
+  assert(isinstance(counts, pd.DataFrame))
+  # Asswert chat df and counts df have same users
+  assert(set(chat.users) == set(counts.columns))
 
- # Check range hours
- assert(counts.index.max() == chat.df.index.month.max())
- assert(counts.index.min() == chat.df.index.month.min())
+  # Check range hours
+  assert(counts.index.max() == chat.df.index.month.max())
+  assert(counts.index.min() == chat.df.index.month.min())
 
 
 def test_interventions_weekday():
 
- filename = 'tests/chats/example_1.txt'
- chat = WhatsAppChat.from_txt(filename)
- counts = interventions(chat, date_mode='weekday', msg_length=False)
+ for filename in filenames:
+  chat = WhatsAppChat.from_txt(filename)
+  counts = interventions(chat, date_mode='weekday', msg_length=False)
 
- assert(isinstance(counts, pd.DataFrame))
- # Asswert chat df and counts df have same users
- assert(set(chat.users) == set(counts.columns))
+  assert(isinstance(counts, pd.DataFrame))
+  # Asswert chat df and counts df have same users
+  assert(set(chat.users) == set(counts.columns))
 
- # Check range hours
- assert(counts.index.max() == chat.df.index.weekday.max())
- assert(counts.index.min() == chat.df.index.weekday.min())
+  # Check range hours
+  assert(counts.index.max() == chat.df.index.weekday.max())
+  assert(counts.index.min() == chat.df.index.weekday.min())
 
 
 
 def test_interventions_weekday_msg_length():
 
- filename = 'tests/chats/example_1.txt'
- chat = WhatsAppChat.from_txt(filename)
- counts = interventions(chat, date_mode='weekday', msg_length=True)
+ for filename in filenames:
+  chat = WhatsAppChat.from_txt(filename)
+  counts = interventions(chat, date_mode='weekday', msg_length=True)
 
- assert(isinstance(counts, pd.DataFrame))
- # Asswert chat df and counts df have same users
- assert(set(chat.users) == set(counts.columns))
+  assert(isinstance(counts, pd.DataFrame))
+  # Asswert chat df and counts df have same users
+  assert(set(chat.users) == set(counts.columns))
 
- # Check range hours
- assert(counts.index.max() == chat.df.index.weekday.max())
- assert(counts.index.min() == chat.df.index.weekday.min())
+  # Check range hours
+  assert(counts.index.max() == chat.df.index.weekday.max())
+  assert(counts.index.min() == chat.df.index.weekday.min())
 
 
 
 def test_interventions_hourweekday():
 
- filename = 'tests/chats/example_1.txt'
- chat = WhatsAppChat.from_txt(filename)
- counts = interventions(chat, date_mode='hourweekday', msg_length=False)
+ for filename in filenames:
+  chat = WhatsAppChat.from_txt(filename)
+  counts = interventions(chat, date_mode='hourweekday', msg_length=False)
 
- assert(isinstance(counts, pd.DataFrame))
- # Asswert chat df and counts df have same users
- assert(set(chat.users) == set(counts.columns))
+  assert(isinstance(counts, pd.DataFrame))
+  # Asswert chat df and counts df have same users
+  assert(set(chat.users) == set(counts.columns))
 
- # Check range days
- assert(counts.index.levels[0].max() == chat.df.index.weekday.max())
- assert(counts.index.levels[0].min() == chat.df.index.weekday.min())
+  # Check range days
+  assert(counts.index.levels[0].max() == chat.df.index.weekday.max())
+  assert(counts.index.levels[0].min() == chat.df.index.weekday.min())
 
- # Check range hours
- assert(counts.index.levels[1].max() == chat.df.index.hour.max())
- assert(counts.index.levels[1].min() == chat.df.index.hour.min())
+  # Check range hours
+  assert(counts.index.levels[1].max() == chat.df.index.hour.max())
+  assert(counts.index.levels[1].min() == chat.df.index.hour.min())
 
 
 def test_interventions_hourweekday_msg_length():
 
- filename = 'tests/chats/example_1.txt'
- chat = WhatsAppChat.from_txt(filename)
- counts = interventions(chat, date_mode='hourweekday', msg_length=True)
+ for filename in filenames:
+  chat = WhatsAppChat.from_txt(filename)
+  counts = interventions(chat, date_mode='hourweekday', msg_length=True)
 
- assert(isinstance(counts, pd.DataFrame))
- # Asswert chat df and counts df have same users
- assert(set(chat.users) == set(counts.columns))
+  assert(isinstance(counts, pd.DataFrame))
+  # Asswert chat df and counts df have same users
+  assert(set(chat.users) == set(counts.columns))
 
- # Check range days
- assert(counts.index.levels[0].max() == chat.df.index.weekday.max())
- assert(counts.index.levels[0].min() == chat.df.index.weekday.min())
+  # Check range days
+  assert(counts.index.levels[0].max() == chat.df.index.weekday.max())
+  assert(counts.index.levels[0].min() == chat.df.index.weekday.min())
 
- # Check range hours
- assert(counts.index.levels[1].max() == chat.df.index.hour.max())
- assert(counts.index.levels[1].min() == chat.df.index.hour.min())
+  # Check range hours
+  assert(counts.index.levels[1].max() == chat.df.index.hour.max())
+  assert(counts.index.levels[1].min() == chat.df.index.hour.min())
 
 def test_interventions_error():
 
- filename = 'tests/chats/example_1.txt'
- chat = WhatsAppChat.from_txt(filename)
- with pytest.raises(ValueError):
- counts = interventions(chat, date_mode='error', msg_length=False)
- with pytest.raises(ValueError):
- counts = interventions(chat, date_mode='error', msg_length=True)
+ for filename in filenames:
+  chat = WhatsAppChat.from_txt(filename)
+  with pytest.raises(ValueError):
+  counts = interventions(chat, date_mode='error', msg_length=False)
+  with pytest.raises(ValueError):
+  counts = interventions(chat, date_mode='error', msg_length=True)