Merge branch 'main' into 14-new-metric-request-number-of-projects

Author: icaoberg

AUTHORS

@@ -4,7 +4,17 @@ Ivan Cao-Berg (icaoberg) - Pittsburgh Supercomputing Center
 ## Undergraduate Students
 Eduardo J. Figueroa (EduardoJFigueroa) - University of Puerto Rico 
 
-# SAMS Data Science Group
+## CS Scholars Data Science Group
+Joshua Franco (francojoshua) - Western High School
+Nicolas Watkins (nicolasw-cmu) - Edmond Santa Fe Highschool
+Carmen Ung (cmucung) - Rosemead High School 
+Marcuslyne Sieh (marcuslynes) - The Metropolitan Regional Career and Technical Center
+Manav Mahida (ManavMahida) - North Penn High School
+Temidayo Ogundare (Togundar) - Science Park High School
+Neptune Barton (jellyfishking-github)- Eldorado High School
+
+
+## SAMS Data Science Group
 Tiffany Wang (Tffny3) - Cupertino High School 
 Eileen Lin (eileen-png) - Eleanor Roosevelt High School, eSTEM Academy
 Louis Lin (Bobvius) - Jack Britt High

braininventory/__init__.py

@@ -1 +1 @@
-from .get import *
+from .get import *

braininventory/get.py

@@ -3,6 +3,7 @@
 import json
 from datetime import date
 
+
 def today():
     """
 	Get today's snapshot of Brain Image Library.
@@ -23,85 +24,130 @@ def today():
     else:
         print("Error: Failed to fetch JSON data")
         return pd.DataFrame()
-    
+
+
 def __get_number_of_datasets(df):
-     return len(df)
+    return len(df)
+
 
 def __get_completeness_score(df):
-      return df['score'].sum()/len(df)
+    return df["score"].sum() / len(df)
+
 
 def __is_reachable(url):
-	response = requests.get(url)
+    response = requests.get(url)
+
+    if response.status_code == 200:
+        return True
+    else:
+        return False
 
-	if response.status_code == 200:
-		return True
-	else:
-		return False
 
 def __get_metadata_version(df):
-    return df['metadata_version'] .value_counts().to_dict()
+    return df["metadata_version"].value_counts().to_dict()
+
 
 def __get_contributor(df):
-    return df['contributor'].value_counts().to_dict()
+    return df["contributor"].value_counts().to_dict()
+
 
 def __get_affilation(df):
-    return df['affiliation'].value_counts().to_dict()
+    return df["affiliation"].value_counts().to_dict()
+
+def __get_awards(df):
+    return df["award_number"].unique()
 
 def __get_award_number(df):
-    return df['award_number'].value_counts().to_dict()
+    return df["award_number"].value_counts().to_dict()
+
 
 def __get_species(df):
-    return df['species'].value_counts().to_dict()
+    return df["species"].value_counts().to_dict()
+
 
 def __get_cnbtaxonomy(df):
-    return df['cnbtaxonomy'].value_counts().to_dict()
+    return df["cnbtaxonomy"].value_counts().to_dict()
+
 
 def __get_samplelocalid(df):
-    return df['samplelocalid'].value_counts().to_dict()
+    return df["samplelocalid"].value_counts().to_dict()
+
 
 def __get_genotype(df):
-    return df['genotype'].value_counts().to_dict()
+    return df["genotype"].value_counts().to_dict()
+
 
 def __get_generalmodality(df):
-    return df['generalmodality'].value_counts().to_dict()
+    return df["generalmodality"].value_counts().to_dict()
+
 
 def __get_technique(df):
-    return df['technique'].value_counts().to_dict()
+    return df["technique"].value_counts().to_dict()
+
 
 def __get_locations(df):
-    return df['locations'].value_counts().to_dict()
+    return df["locations"].value_counts().to_dict()
 
-def report():
-    # Get today's date
-	tdate = date.today()
-
-	# Convert date to string
-	tdate = tdate.strftime("%Y-%m-%d")
-        
-	df = today()
-
-	report = {}
-	report['date'] = tdate
-	report['number_of_datasets'] = __get_number_of_datasets(df)
-	report['completeness_score'] = __get_completeness_score(df)
-	report['metadata_version'] = __get_metadata_version(df)
-    report['contributor'] =  __get_contributor(df)
-    report['affiliation'] =  __get_affilation(df)
-    report['award_number'] = __get_award_number(df)
-    report['species'] = __get_species(df)
-    report['cnbtaxonomy'] = __get_cnbtaxonomy(df)
-    report['samplelocalid'] = __get_samplelocalid(df)
-    report['genotype'] = __get_genotype(df)
-    report['generalmodality'] = __get_generalmodality(df)
-    report['technique'] = __get_technique(df)
-    report['locations'] = __get_locations(df)
-     
-	report['is_reachable'] = df['URL'].apply(__is_reachable)
-
-	return report
-
-def __get_num_of_projects(df): 
+def __get_contributors(df):
+    """
+    This returns an array of contributor names from the contributorname column.
+    """
+    return df["contributorname"].unique()
+
+
+def __get_project_names(df):
+	'''
+	Gets the unique list of project names.
+
+    Input: dataframe
+    Output: list 
     '''
-    Returns the number of unique projects in dataframe.
+	return df['project'].unique()
+
+def __get_list_of_projects(df):
+    '''
+    Get the list of names for unique projects
+
+    Input parameter: dataframe
+    Output:  list of projects
     '''
-    return df['project'].value_counts().to_dict() 
+    
+    return df['project'].unique().to_dict()
+
+def __get_number_of_projects(df):
+    '''
+    Get the number of unique projects
+
+    Input parameter: dataframe
+    Output:  number of projects
+    '''
+    
+    return len(df['project'].unique())
+
+def report():
+    # Get today's date
+    tdate = date.today()
+
+    # Convert date to string
+    tdate = tdate.strftime("%Y-%m-%d")
+
+    df = today()
+
+    report = {}
+    report["date"] = tdate
+    report["number_of_datasets"] = __get_number_of_datasets(df)
+    report["completeness_score"] = __get_completeness_score(df)
+    report["metadata_version"] = __get_metadata_version(df)
+    report["contributor"] = __get_contributor(df)
+    report["affiliation"] = __get_affilation(df)
+    report["award_number"] = __get_award_number(df)
+    report["species"] = __get_species(df)
+    report["cnbtaxonomy"] = __get_cnbtaxonomy(df)
+    report["samplelocalid"] = __get_samplelocalid(df)
+    report["genotype"] = __get_genotype(df)
+    report["generalmodality"] = __get_generalmodality(df)
+    report["technique"] = __get_technique(df)
+    report["locations"] = __get_locations(df)
+    report["is_reachable"] = df["URL"].apply(__is_reachable)
+
+    return report