Added homework 3!!

hw3/etl.py

+'''
+The etl module defines basic language primitives for manipulating Pandas
+DataFrames. It takes a DataFrame in and outputs a transformed DataFrame.
+You will implement several of the routines to perform these transformations.
+
+Example Usage:
+
+You can create DataFrame and create an ETL class that takes the DataFrame
+as input.
+
+>> df1 = pd.DataFrame([['Bob', 'Stewart'],
+                       ['Anna', 'Davis'],
+                       ['Jerry', 'Dole'],
+                       ['John', 'Marsh']],
+                      columns=["first_name", "last_name"])
+>> etl = ETL(df1)
+
+The add() function creates a new column with a specified value:
+
+>> etl.add(colname="age", 0)
+>> pw1.df
+  first_name last_name  age
+0        Bob   Stewart    0
+1       Anna     Davis    0
+2      Jerry      Dole    0
+3       John     Marsh    0
+'''
+
+import pandas as pd
+import re
+
+
+class ETL:
+    '''
+    The class that defines ETL transformations for a single dataframe
+    '''
+
+    def __init__(self, df: pd.DataFrame):
+        '''
+        ETL objects are constructed with a source
+        dataframe. These dataframes are manipulated
+        in-place.
+        '''
+
+        #how to access the source dataframe
+        self.df = df
+
+        #stores a history of the transformations to the df
+        self.transforms = []
+
+
+    def add(self, colname, x):
+        '''
+        The add(colname, x) function adds a column with the specified name
+        (colname) and a specified value (x). It adds this value to
+        all rows of the dataframe. We've implemented this as an
+        example to show you how to structure your ETL functions. 
+
+        add *modifies* self.df as well as *returns* it
+        '''
+
+        #Test to see if colname is None, if so use a default colname
+        self.df[colname] = x
+
+        #append your changes to the transform list
+        self.transforms.append(self.df.copy(deep=True))
+        return self.df
+
+
+
+    def drop(self, colname):
+        '''
+        The drop(colname) function returns a DataFrame 
+        with the column (colname) removed.
+
+        drop *modifies* self.df as well as *returns* it
+        '''
+
+        #YOUR CODE HERE
+
+        self.transforms.append(self.df.copy(deep=True))
+        return self.df
+
+    def copy(self, colname, new_colname):
+        '''
+        copy(colname, new_colname) duplicates a column and 
+        saves it to the new_colname.
+
+        copy *modifies* self.df as well as *returns* it.
+        '''
+
+        #YOUR CODE HERE
+
+        self.transforms.append(self.df.copy(deep=True))
+        return self.df
+
+
+    def split(self, colname, new_colname, splitter):
+        '''
+        split(colname, new_colname, splitter) takes a column
+        splits the value on a delimiter. It replaces colname
+        with the substrings that appear before the delimiter
+        and puts the values after the delimiter in the 
+        new_colname. If the string does not contain the delimiter
+        then new_colname is assigned an empty string.
+
+        split *modifies* self.df as well as *returns* it.
+        '''
+
+        #YOUR CODE HERE
+
+
+        self.transforms.append(self.df.copy(deep=True))
+        return self.df
+
+
+    def merge(self, col1, col2, splitter):
+        '''
+        merge(col1, col2, splitter) replaces col1
+        with the values of col1 and col2 concatenated,
+        and seperated by the delimiter. The delimiter is
+        ignored if either df.col1 or df.col2 is an empty 
+        string.
+
+        merge *modifies* self.df as well as *returns* it. 
+        '''
+
+        #YOUR CODE HERE
+
+
+        self.transforms.append(self.df.copy(deep=True))
+        return self.df
+
+
+    def format(self, colname, fn):
+        '''
+        format applies an input function to every value in colname. fn
+        is a *function*.
+
+        format *modifies* self.df as well as *returns* it.
+        '''
+        
+        #YOUR CODE HERE
+
+
+        self.transforms.append(self.df.copy(deep=True))
+        return self.df
+
+
+    def divide(self, colname, new_colname1, new_colname2, condition):
+        '''
+        Divide conditionally divides a column, sending values that 
+        satisfy the condition into one of two columns 
+        (new_colname1 or new_colname2). condition is a Boolean function
+        of values.
+
+        See examples in the writeup.
+        '''
+
+        #YOUR CODE HERE
+
+        self.transforms.append(self.df.copy(deep=True))
+        return self.df

hw3/etl_programs.py

+'''
+Here, you will write programs that transform dataframes
+using the functions that you wrote.
+'''
+
+def phone():
+    '''
+    Write an ETL program that results in a
+    dataframe with two columns: area_code, phone_number.
+    '''
+    df = pd.DataFrame([['(408)996-758'],
+                      ['+1 667 798 0304'],
+                      ['(774)998-758'],
+                      ['+1 442 030 9595']],
+                      columns=["phoneno"])
+    etl = ETL(df)
+
+
+    #Your code goes here
+
+
+    return etl.df
+
+
+def date():
+    '''
+    Write an ETL program that results in a
+    dataframe with three columns: day, month, year.
+    The day must be in two-digit format i.e, 01, 08.
+    The month must be the full month name, e.g., "May".
+    The year must be in YYYY format.
+    '''
+    df = pd.DataFrame([['03/2/1990'],
+                      ['2/14/1964'],
+                      ['1990-04-30'],
+                      ['7/9/2012'],
+                      ['1989-09-13'],
+                      ['1994-08-21'],
+                      ['1996-11-30'],
+                      ['2004-12-23'],
+                      ['4/21/2016']]
+                      columns=["date"])
+    etl = ETL(df)
+
+
+    #Your code goes here
+
+
+    return etl.df
+
+
+def name():
+    '''
+    Write an ETL program that correctly formats names
+    into first_name and last_name.
+    '''
+    df = pd.DataFrame([['Such,Bob', ''],
+                    ['Ann', 'Davis'],
+                    ['Dole,Jerry', ''],
+                    ['Joan', 'Song']],
+                     columns=["first_name", "last_name"])
+    etl = ETL(df)
+
+
+    #Your code goes here
+
+
+    return etl.df
\ No newline at end of file