mobilizr-python 0.94__tar.gz

mobilizr_python-0.94/MANIFEST.in

@@ -0,0 +1 @@
+include my_datasets_lib/data/*.csv

mobilizr_python-0.94/PKG-INFO

@@ -0,0 +1,16 @@
+Metadata-Version: 2.4
+Name: mobilizr-python
+Version: 0.94
+Summary: A library of custom datasets.
+Home-page: https://github.com/emilio-dulay/my_datasets_lib
+Author: Emilio Dulay
+Author-email: emiliodulay19@g.ucla.edu
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Requires-Dist: pandas
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: home-page
+Dynamic: requires-dist
+Dynamic: summary

mobilizr_python-0.94/README.md

@@ -0,0 +1,30 @@
+# UCLA IDS Data Library
+
+A lightweight Python library for loading example datasets used in data science courses.
+
+---
+
+## Installation
+
+Clone the repository and install locally:
+git clone https://github.com/EmilioD19/UCLA-IDS-Data-Library.git
+cd UCLA-IDS-Data-Library
+pip install .
+
+## Usage
+Import functions:
+from my_datasets_lib import load, describe, list_datasets
+
+## Load a dataset
+df = load("iris")
+print(df.head())
+
+## Describe a dataset
+print(describe("iris"))
+
+## List available datasets
+print(list_datasets())
+
+## Error Handling
+If a dataset does not exist, ValueError is raised:
+load("nonexistent")

mobilizr_python-0.94/mobilizr-python/__init__.py

@@ -0,0 +1,45 @@
+from . import datasets
+import pandas as pd
+
+def data(name):
+    """Load a dataset by name."""
+    if hasattr(datasets, name):
+        return getattr(datasets, name).load()
+    else:
+        raise ValueError(f"Dataset '{name}' not found in my_datasets_lib.datasets")
+    
+    
+def describe(name):
+    """Get the description for a dataset by name."""
+    if hasattr(datasets, name):
+        return getattr(datasets, name).describe()
+    else:
+        raise ValueError(f"Dataset '{name}' not found in my_datasets_lib.datasets")
+    
+def list_datasets():
+    """Return a list of available dataset names."""
+    return [name for name in dir(datasets) if not name.startswith("_")]
+
+def View(name):
+    """View a dataset by name."""
+    if hasattr(datasets, name):
+        df = getattr(datasets, name).load()
+        if isinstance(df, pd.DataFrame):
+            return df
+        else:
+            raise TypeError(f"Dataset '{name}' is not a pandas DataFrame.")
+    else:
+        raise ValueError(f"Dataset '{name}' not found in my_datasets_lib.datasets")
+    
+def timeuse_format(df):
+    df = df.replace("NOT_DISPLAYED", 0)
+    df[df.columns.difference(['user.id', 'timestamp', 'activities'])] = \
+        df[df.columns.difference(['user.id', 'timestamp', 'activities'])].apply(pd.to_numeric)
+
+    submissions = df.groupby('user.id').size().rename("submissions")
+    
+    averages = df.groupby('user.id').mean(numeric_only = True)
+    
+    return averages.merge(submissions, on = "user.id")
+
+

mobilizr_python-0.94/mobilizr-python/datasets/__init__.py

@@ -0,0 +1,7 @@
+'''Makes datasets behave like bundles of submodules.'''
+
+from . import cdc, food_ids, atu_dirty, atu_clean, timeuse_ids, timeuse_ids_clean
+
+__all__ = ["cdc", "food_ids", "atu_dirty", "atu_clean", "timeuse_ids",
+           "timeuse_ids_clean"]
+

mobilizr_python-0.94/mobilizr-python/datasets/atu_clean.py

@@ -0,0 +1,41 @@
+import os
+import pandas as pd
+
+def load():
+    """Load the atu_clean dataset."""
+    path = os.path.join(os.path.dirname(__file__), '..', 'data', 'atu_clean.csv')
+    df = pd.read_csv(path)
+    return df
+
+def describe():
+    """Return a description of the atu_clean dataset."""
+    return '''
+American Time Use Survey Data Sample - Clean
+Description
+A dataset containing a subset of variables from the American Time Use Survey. This dataset is a cleaned version of atu_dirty.
+
+Usage
+data(atu_clean)
+Format
+A data frame with 10,493 observations of 8 variables
+
+Details
+caseid. unique identifier of individual survey participant
+
+age. the age of the respondent
+
+sex. the sex of the respondent
+
+fulltime_emp. the employment status of the respondent
+
+phys_challenge. does the respondent have a physical difficulty
+
+sleep. the length of time the person sleeps, in minutes
+
+homework. How long the respondent spent on homework assignments, in minutes
+
+socializing. the number of minutes the respondent spent socializing
+
+Source
+http://www.bls.gov/tus/
+'''

mobilizr_python-0.94/mobilizr-python/datasets/atu_dirty.py

@@ -0,0 +1,43 @@
+import os
+import pandas as pd
+
+def load():
+    """Load the atu_dirty dataset."""
+    path = os.path.join(os.path.dirname(__file__), '..', 'data', 'atu_dirty.csv')
+    df = pd.read_csv(path)
+    return df
+
+def describe():
+    """Return a description of the atu_dirty dataset."""
+    return 
+'''
+American Time Use Survey Data Sample - Dirty
+Description
+A dataset containing a subset of variables from the American Time Use Survey. This dataset is "dirty", meaning it has elements which require formatting before use.
+
+Usage
+data(atu_dirty)
+Format
+A data frame with 10,493 observations of 8 variables
+
+Details
+caseid. unique identifier of individual survey participant
+
+V1. the age of the respondent
+
+V2. the gender of the respondent (1: Male, 2: Female)
+
+V3. the employment status of the respondent
+
+V4. does the respondent have a physical difficulty (1: Person did not report having a physical difficulty, 2: Person surveyed reported the have a physical difficulty)
+
+V5. the length of time the person sleeps, in minutes
+
+V6. How long the respondent spent on homework assignments, in minutes
+
+V7. the number of minutes the respondent spent socializing
+
+Source
+http://www.bls.gov/tus/
+'''.strip()
+

mobilizr_python-0.94/mobilizr-python/datasets/cdc.py

@@ -0,0 +1,61 @@
+import os
+import pandas as pd
+
+def load():
+    """Load the cdc dataset."""
+    path = os.path.join(os.path.dirname(__file__), '..', 'data', 'cdc.csv')
+    df = pd.read_csv(path)
+    return df
+
+def describe():
+    """Return a description of the CDC dataset."""
+    return """
+    CDC Youth Risk Behavior Survey Data
+
+    **Description**
+    A dataset containing responses from the 2021 CDC Youth Risk Behavior Survey.
+
+    **Usage**
+    `data(cdc)`
+
+    **Format**
+    A data frame with 17,232 observations of 32 variables.
+
+    **Details**
+    - **age** — age in years  
+    - **sex** — sex assigned at birth  
+    - **grade** — grade in school  
+    - **height** — height of student in meters  
+    - **weight** — weight of student in kilograms  
+    - **seat_belt** — how often student wore a seatbelt in a motor vehicle driven by someone else  
+    - **drive_text** — how often the student reported texting while driving in the past 30 days  
+    - **hisp_latino** — whether or not student identifies as Hispanic or Latino  
+    - **american_indian_or_alaska_native** — whether or not student identifies as American Indian or Alaska Native  
+    - **asian** — whether or not student identifies as Asian  
+    - **black_or_african_american** — whether or not student identifies as Black or African American  
+    - **native_hawaiian_or_other_pacific_islander** — whether or not student identifies as Native Hawaiian or other Pacific Islander  
+    - **white** — whether or not student identifies as White  
+    - **bully_school** — did the student report being bullied at school  
+    - **bully_electronic** — did the student report being bullied online  
+    - **depressed** — student reported feeling depressed for 2 weeks in a row or more during the past 12 months  
+    - **days_smoking** — number of days student reported smoking cigarettes during past 30 days  
+    - **days_vaping** — number of days student reported vaping/smoking electronic cigarettes during past 30 days  
+    - **sexuality** — how the student describes their sexual orientation  
+    - **describe_weight** — student perception of their weight relative to what they believe it should be  
+    - **drink_juice** — how often student consumed fruit juice over the previous 7 days  
+    - **eat_fruit** — how often student ate fruit over the previous 7 days  
+    - **eat_salad** — how often student ate salad over the previous 7 days  
+    - **drink_soda** — how often student consumed soda over the previous 7 days  
+    - **drink_milk** — how often student drank milk over the previous 7 days  
+    - **eat_breakfast** — how often the student reported eating breakfast over the past 7 days  
+    - **days_exercise_60** — how often student was active for at least 60 mins over the previous 7 days  
+    - **screen_time** — average number of hours spent on a screen on a school day  
+    - **number_teams** — number of sports teams played on during previous 12 months  
+    - **hours_sleep** — reported hours of sleep on school nights  
+    - **drink_sportdrink** — how often student consumed sports drinks over the past 7 days  
+    - **drink_water** — how often student consumed water over the past 7 days
+
+    **Source**
+    http://www.cdc.gov/HealthyYouth/yrbs/index.htm
+        """.strip()
+

mobilizr_python-0.94/mobilizr-python/datasets/food_ids.py

@@ -0,0 +1,8 @@
+import os
+import pandas as pd
+
+def load():
+    """Load the food dataset."""
+    path = os.path.join(os.path.dirname(__file__), '..', 'data', 'food_ids.csv')
+    df = pd.read_csv(path)
+    return df

mobilizr_python-0.94/mobilizr-python/datasets/timeuse_ids.py

@@ -0,0 +1,8 @@
+import os
+import pandas as pd
+
+def load():
+    """Load the timeuse_ids dataset."""
+    path = os.path.join(os.path.dirname(__file__), '..', 'data', 'timeuse_ids.csv')
+    df = pd.read_csv(path)
+    return df

mobilizr_python-0.94/mobilizr-python/datasets/timeuse_ids_clean.py

@@ -0,0 +1,8 @@
+import os
+import pandas as pd
+
+def load():
+    """Load the timeuse_ids_clean dataset."""
+    path = os.path.join(os.path.dirname(__file__), '..', 'data', 'timeuse_ids_clean.csv')
+    df = pd.read_csv(path)
+    return df

mobilizr_python-0.94/mobilizr_python.egg-info/PKG-INFO

@@ -0,0 +1,16 @@
+Metadata-Version: 2.4
+Name: mobilizr-python
+Version: 0.94
+Summary: A library of custom datasets.
+Home-page: https://github.com/emilio-dulay/my_datasets_lib
+Author: Emilio Dulay
+Author-email: emiliodulay19@g.ucla.edu
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Requires-Dist: pandas
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: home-page
+Dynamic: requires-dist
+Dynamic: summary

mobilizr_python-0.94/mobilizr_python.egg-info/SOURCES.txt

@@ -0,0 +1,16 @@
+MANIFEST.in
+README.md
+setup.py
+mobilizr-python/__init__.py
+mobilizr-python/datasets/__init__.py
+mobilizr-python/datasets/atu_clean.py
+mobilizr-python/datasets/atu_dirty.py
+mobilizr-python/datasets/cdc.py
+mobilizr-python/datasets/food_ids.py
+mobilizr-python/datasets/timeuse_ids.py
+mobilizr-python/datasets/timeuse_ids_clean.py
+mobilizr_python.egg-info/PKG-INFO
+mobilizr_python.egg-info/SOURCES.txt
+mobilizr_python.egg-info/dependency_links.txt
+mobilizr_python.egg-info/requires.txt
+mobilizr_python.egg-info/top_level.txt

mobilizr_python-0.94/mobilizr_python.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

mobilizr_python-0.94/mobilizr_python.egg-info/requires.txt

@@ -0,0 +1 @@
+pandas

mobilizr_python-0.94/mobilizr_python.egg-info/top_level.txt

@@ -0,0 +1 @@
+mobilizr-python

mobilizr_python-0.94/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

mobilizr_python-0.94/setup.py

@@ -0,0 +1,19 @@
+from setuptools import setup, find_packages
+
+setup(
+    name='mobilizr-python',
+    version='0.94',
+    packages=find_packages(),
+    include_package_data=True,
+    install_requires=[
+        'pandas',
+    ],
+    description='A library of custom datasets.',
+    author='Emilio Dulay',
+    author_email='emiliodulay19@g.ucla.edu',
+    url="https://github.com/emilio-dulay/my_datasets_lib",
+    classifiers=[
+        'Programming Language :: Python :: 3',
+        'License :: OSI Approved :: MIT License',
+    ],
+)