255 \begin{frame}

   256   \frametitle{Statistical Analysis and Parsing}

   257   Read the data supplied in \emph{sslc1.txt} and obtain the following statistics:

   258   \begin{itemize}

   259     \item Average total marks scored in each region

   260     \item Subject wise average score of each region

   261     \item ??Subject wise average score for all regions combined??

   262   \end{itemize}

   263 \end{frame}

   264 

   265 \begin{frame}

   266   \frametitle{Statistical Analysis and Parsing \ldots}

   267   Machinery Required -

   268   \begin{itemize}

   269     \item File reading and parsing

   270     \item NumPy arrays - sum by rows and sum by coloumns

   271     \item Dictionaries

   272   \end{itemize}

   273 \end{frame}

   274 

   275 \begin{frame}

   276   \frametitle{File reading and parsing}

   277   Understanding the structure of sslc1.txt

   278   \begin{itemize}

   279     \item Each line in the file, i.e each row of a file is a single record.

   280     \item Each record corresponds to a record of a single student

   281     \item Each record consists of several fields separated by a ';'

   282   \end{itemize}

   283 \end{frame}

   284 

   285 \begin{frame}

   286   \frametitle{File reading and parsing \ldots}

   287   Each record consists of:

   288   \begin{itemize}

   289     \item Region Code

   290     \item Roll Number

   291     \item Name

   292     \item Marks of 5 subjects

   293     \item Total marks

   294     \item Pass (P)

   295     \item Withdrawn (W)

   296     \item Fail (F)

   297   \end{itemize}

   298 \end{frame}

   299 

   300 \begin{frame}[fragile]

   301   \frametitle{File reading and parsing \ldots}

   302   \begin{lstlisting}

   303 for record in open('sslc1.txt'):

   304     fields = record.split(';')

   305   \end{lstlisting}

   306 \end{frame}

   307 

   308 \begin{frame}[fragile]

   309   \frametitle{Dictionary}

   310   \begin{itemize}

   311     \item lists index: 0 \ldots n

   312     \item dictionaries index using any hashable objects

   313     \item d = \{ ``Hitchhiker's guide'' : 42, ``Terminator'' : ``I'll be back''\}

   314     \item d[``Terminator''] => ``I'll be back''

   315     \item ``Terminator'' is called the key of \typ{d}

   316     \item ``I'll be back'' is called the value of the key ``Terminator''

   317   \end{itemize}

   318 \end{frame}

   319 

   320 \begin{frame}[fragile]

   321   \frametitle{Dictionary - Building parsed data}

   322   \begin{itemize}

   323     \item Let the parsed data be stored in dictionary \typ{data}

   324     \item Keys of \typ{data} are strings - region codes

   325     \item Value of the key is another dictionary.

   326     \item This dictionary contains:

   327     \begin{itemize}

   328       \item 'marks': A list of NumPy arrays

   329       \item 'total': Total marks of each student

   330       \item 'P': Number of passes

   331       \item 'F': Number of failures

   332       \item 'W': Number of withdrawls

   333     \end{itemize}

   334   \end{itemize}

   335 \end{frame}

   336 

   337 \begin{frame}[fragile]

   338   \frametitle{Dictionary - Building parsed data \ldots}

   339   \small

   340   \begin{lstlisting}

   341 data = {}

   342 for record in open('sslc1.txt'):

   343     fields = record.split(';')

   344     if fields[0] not in data:

   345         data[fields[0]] = {

   346             'marks': array([]),

   347             'total': array([]),

   348             'P': 0,

   349             'F': 0,

   350             'W': 0

   351             }

   352   \end{lstlisting}

   353 \end{frame}

   354 

   355 \begin{frame}[fragile]

   356   \frametitle{Dictionary - Building parsed data \ldots}

   357   \small

   358   \begin{lstlisting}

   359 data[fields[0]]['marks'] = append(

   360     data[fields[0]]['marks'], 

   361     [int(fields[3]), int(fields[4]),

   362     int(fields[5]), int(fields[6]),

   363     int(fields[7])

   364     ])

   365 

   366 data[fields[0]]['total'].append(fields[8])

   367 

   368 pfw_key = fields[9] or fields[10] or fields[11]

   369 data[fields[0]][pfw_key] += 1

   370   \end{lstlisting}

   371 \end{frame}

   372 

   373 \begin{frame}[fragile]

   374   \frametitle{Calculations}

   375   \begin{lstlisting}

   376 all_sub_avg = array([])

   377 for k, v in data:

   378     data[k]['avg'] = average(

   379         data[k]['total'])

   380     data[k]['sub_avg'] = average(

   381         data[k]['marks'], axis=1)

   382   \end{lstlisting}

   383 \end{frame}

   384