Adding a small python code using Panda library

Zooid_Vis/bin/data/student_db_mange.py

@@ -0,0 +1,162 @@
+import pandas as pd
+import os
+
+
+class StudentDataBase:
+    def __init__(self,filename='student-dataset.csv'):
+        self.filename = filename
+        self.clean_data_base()
+        self.add_avg()
+        self.save()
+
+    def clean_data_base(self):
+        '''
+        clean the Data set from col (info) that i dont care.
+        We have 2 Option:
+        Option 1: give the header of the col and remove it with columns
+        Option 2: give the index of col we want to remove
+        '''
+        self.students= pd.read_csv(self.filename)
+        # Remvoe those col in the begnning (and check if it's not already if i rerun it..)
+        columns_to_drop = ['latitude', 'longitude', 'ethnic.group', 'language.grade', 'portfolio.rating', 'coverletter.rating', 'refletter.rating']
+        existing_columns_to_drop = [col for col in columns_to_drop if col in self.students.columns]
+        if existing_columns_to_drop:
+             self.students.drop(columns=existing_columns_to_drop, inplace=True)
+        # removing with Index
+
+        # indices_to_drop = list(range(8, 15)) + list(range(3, 6))
+        # existing_indices_to_drop = [idx for idx in indices_to_drop if idx in self.students.index]
+        # if existing_indices_to_drop:
+        #     self.students.drop(index=existing_indices_to_drop, inplace=True)
+
+
+        # Mix the removing: 
+        # list_idx_remove = list(range(8,13)) + list(range(3,5))
+
+    def save(self):
+        self.students.to_csv(self.filename,index=False)
+
+
+    def add_avg(self):
+        self.students['Average Grade'] = self.students[["math.grade", "english.grade", "sciences.grade"]].mean(axis=1)
+
+    def removre_student(self,name):
+        self.students = self.students[self.students['name'] != name]
+        # For memory efficiency :
+        #self.students.drop(self.students[self.students["name"] == name].index, inplace=True)
+
+    def update_grade(self,name,english = None ,math=None, science = None):
+
+        if self.students[self.students['name'] == name].empty:
+            print("No such student exist")
+            return
+
+        if english:
+            self.students.loc[self.students['name'] == name ,'english.grade'] = english
+        if math:
+            self.students.loc[self.students['name'] == name ,'math.grade'] = math
+        if science:
+            self.students.loc[self.students['name'] == name ,'sciences.grade'] = science
+
+        self.save()
+
+    def get_student_as_panda(self,id):
+        '''
+        returning a panda type
+        '''
+        student_data = self.students[self.students['id'] == id]
+        if student_data.empty:
+            return None
+        return student_data
+
+    def get_student_as_Student_class(self,id):
+        '''
+        using argws to pass as arguments to the constructor for the Student class (**stu_dic)
+        '''
+        student_data = self.students[self.students['id'] == id]
+        if student_data.empty:
+            return None
+        stu_dic = student_data.iloc[0].to_dict()
+        # Replace the key "english.grade" with "english"
+        if 'english.grade' in stu_dic:
+            stu_dic['english'] = stu_dic.pop('english.grade')
+        if 'math.grade' in stu_dic:
+            stu_dic['math'] = stu_dic.pop('math.grade')
+        if 'sciences.grade' in stu_dic:
+            stu_dic['science'] = stu_dic.pop('sciences.grade')
+
+        stu_dic.pop('Average Grade')
+        print(stu_dic)
+        return Student(**stu_dic)
+
+    def get_database(self):
+        return self.students
+
+
+    def count_country(self, nationality):
+        '''
+        Option 1: shape will return the dimension of the Data, so if i sort the shape
+            of rows will be the number
+        Option 2: count() will return the summary of each col to the querey is use:
+                # filtered_df = self.students[self.students['nationality'] == nationality]
+                # return filtered_df['nationality'].count()
+        '''
+        return self.students[self.students['nationality'] == nationality].shape[0]
+
+
+class Student(StudentDataBase) :
+    def __init__(self,id=None,name=None,nationality=None,city=None,gender=None,age=None,english=None,math=None,science=None):
+        super().__init__()
+        self.id = id
+        self.name = name
+        self.nationality = nationality
+        self.city = city
+        self.age = age
+        self.gender = gender
+        self.english_grade = english
+        self.math_grade = math
+        self.science_grade = science
+        if id != None:
+            self.add_student()
+
+
+    def add_student(self):
+        temp_db = pd.DataFrame([{
+            "id" : self.get_next_id(),
+            "name": self.name,
+            "nationality": self.nationality,
+            "city": self.city,
+            "gender": self.gender,
+            "age": self.age,
+            "english.grade": self.english_grade,
+            "math.grade": self.math_grade,
+            "sciences.grade": self.science_grade,
+            "Average Grade" : self.avg()
+        }])
+        self.students = pd.concat([self.students,temp_db ] , ignore_index=True)
+        self.save()
+
+    def __str__(self):
+        return f"Student name {self.name} have GPA of {self.avg()}"
+
+    def get_next_id(self):
+        if self.students.empty:
+            return 1
+        else:
+            return self.students['id'].max()+1
+
+    def avg(self):
+        return (self.math_grade + self.english_grade + self.science_grade) / 3
+
+
+
+
+
+DB = StudentDataBase()
+Student(12504,"John Doe", "USA", "New York", "Male", 20, 85, 90, 88)
+df = DB.get_database()
+
+print(DB.count_country('Mexico'))
+stu = DB.get_student_as_Student_class(179)
+(print(stu))
+