Catherine Harvey Project Outline

.ipynb_checkpoints/setup-checkpoint.py

@@ -0,0 +1,27 @@
+
+import setuptools
+
+
+with open("README.md", "r") as fh:
+    long_description = fh.read()
+
+setuptools.setup(
+    name="tetrad_analysis", 
+    version="0.0.1",
+    author="Catherine_Harvey",
+    author_email="[email protected]",
+    description="A package to help analyze tetrads",
+    long_description= "A package to facilitate analyzing the antibiotic markers of yeast tetrads",
+    long_description_content_type="text/markdown",
+    url="https://github.com/harveycas/project_spring_2020",
+    packages=setuptools.find_packages(),
+    install_requires =['xlsxwriter'],
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+    ],
+    python_requires='>=3.6',
+
+)
+

README.md

@@ -1,3 +1,27 @@
 # project_spring_2020
 
 [![CircleCI](https://circleci.com/gh/biof309/project_spring_2020/tree/master.svg?style=shield)](https://circleci.com/gh/biof309/project_spring_2020/tree/master)
+
+
+# Tetrad Analysis
+
+This package will allow for the user to upload an excel file consisting of tetrad information containing sample numbers and 1s and 0s, and allow for the user to sort their data by drug markers.  Afterwards, the user can combine all their sorted data and create a new excel document that contains sheets for each drug marker.  In these sheets, the positive marked spores that were filtered will be listed there.
+
+# Imported file being used for practice
+
+from tetrad_analysis import python_test_list.xlsx
+
+# Steps of the program
+
+1. import an excel document of choice and convert it into a dataframe that can be used by the program
+2. sort this input by positive values for drug markers (in this case it would be the columns) and create separate dataframes for each drug marker
+3. combine these dataframes into a single library that will be labeled all_positive
+4. convert this library into a new excel document that will separate each drug marker into its own sheet
+
+
+# Purpose for this program
+
+This program will facilitate the process of sorting through data.  There can be over hundreds of samples of tetrad data for analysis.  It would take a long time to sort this amount.  Therefore, by having a program that does it, it would save time.
+
+# Contact
+Catherine Harvey ([email protected])

build/lib/tetrad_analysis/dataframe_functions.py

@@ -0,0 +1,84 @@
+import pandas as pd
+import numpy as np
+import ast
+from pandas import ExcelWriter
+from pandas import ExcelFile
+
+#reading the excel file that includes all of the tetrad data
+df = pd.read_excel('python_test_list.xlsx')
+
+
+def open_tetrad(excel):
+    """cleaning a specific document from your computer"""
+
+    #delete the automatically generated column on the left-hand side
+    df_index = df.set_index(first_column)
+    df_index = df.set_index('Plate')
+    print(df_index)
+
+
+def sort_NAT(excel):
+    '''This will allow for you to select for spores in tetrads that test positive for NAT and place them in their own excel document'''
+
+
+    #separate the positive spores from the negative spores
+    df_index.sort_values(['NAT'], ascending=False)
+    NAT_positive = df_index[df_index['NAT'] > 0]
+    print(NAT_positive)
+
+
+
+    #now take the positive ones and put them into their own excel document
+    dfNAT = pd.DataFrame(NAT_positive)
+    dfNAT.to_excel("NAT_positive_python_fp.xlsx")
+
+
+
+
+
+def sort_HYG():
+    '''this will allow for you to select for spores in tetrads that test positive for HYG and place them in their own excel document'''
+
+    #separate the positive spores from the negative spores
+    sort_by_HYG = df_index.sort_values(['HYG'], ascending=False)
+    HYG_positive = df_index[df_index['HYG'] > 0]
+    print(HYG_positive)
+
+    #now take only the positive ones and place them in their own excel document
+    dfNAT = pd.DataFrame(HYG_positive)
+    dfNAT.to_excel("HYG_positive_python_fp.xlsx")
+
+
+
+
+
+def sort_URA():
+    '''this will allow for you to select for spores in tetrads that test positiev for URA and place them in their own excel document'''
+
+    #separate the positive spores from the negative spores
+    sort_by_URA = df_index.sort_values(['URA'], ascending=False)
+    URA_positive = df_index[df_index['URA'] > 0]
+    print(URA_positive)
+
+    #now take only the positive ones and place them in their own document
+    dfNAT = pd.DataFrame(URA_positive)
+    dfNAT.to_excel("URA_positive_python_fp.xlsx")
+
+
+def combine_antibiotics():
+    '''this will take the three marker documents that you made and place them in one major excel document where each marker is one sheet of the document'''
+
+    #create one dataframe containing all of the positive markers
+    all_positive = {'NAT_plus': NAT_positive, 'HYG_plus': HYG_positive, 'URA_plus': URA_positive}
+
+    #turn this new combined dataframe into an excel document
+    writer = pd.ExcelWriter('Antibiotic_markers.xlsx', engine='xlsxwriter')
+
+    for sheet_name in all_positive.keys():
+        all_positive[sheet_name].to_excel(writer, sheet_name=sheet_name, index=False)
+
+    writer.save()
+
+
+
+

build/lib/tetrad_analysis/main.py

@@ -0,0 +1,4 @@
+def main():
+
+if __name__ == '__main__':
+    main()