pandas

#Apply function

#Create a new function:
def num_missing(x):
  return sum(x.isnull())

#Applying per column:
print "Missing values per column:"
print data.apply(num_missing, axis=0) #axis=0 defines that function is to be applied on each column

#Applying per row:
print "\nMissing values per row:"
print data.apply(num_missing, axis=1).head() #axis=1 defines that function is to be applied on each row




# Pivot Table

#Determine pivot table
impute_grps = data.pivot_table(values=["LoanAmount"], index=["Gender","Married","Self_Employed"], aggfunc=np.mean)
print impute_grps


#Multi Indexing

#iterate only through rows with missing LoanAmount
for i,row in data.loc[data['LoanAmount'].isnull(),:].iterrows():
  ind = tuple([row['Gender'],row['Married'],row['Self_Employed']])
  data.loc[i,'LoanAmount'] = impute_grps.loc[ind].values[0]

#Now check the #missing values again to confirm:
print data.apply(num_missing, axis=0)


#Crosstab

def percConvert(ser):
  return ser/float(ser[-1])
  pd.crosstab(data["Credit_History"],data["Loan_Status"],margins=True).apply(percConvert, axis=1)
  
  
  
  # Cut function for binning
  
  #Binning:
def binning(col, cut_points, labels=None):
  #Define min and max values:
  minval = col.min()
  maxval = col.max()

  #create list by adding min and max to cut_points
  break_points = [minval] + cut_points + [maxval]

  #if no labels provided, use default labels 0 ... (n-1)
  if not labels:
    labels = range(len(cut_points)+1)

  #Binning using cut function of pandas
  colBin = pd.cut(col,bins=break_points,labels=labels,include_lowest=True)
  return colBin

#Binning age:
cut_points = [90,140,190]
labels = ["low","medium","high","very high"]
data["LoanAmount_Bin"] = binning(data["LoanAmount"], cut_points, labels)
print pd.value_counts(data["LoanAmount_Bin"], sort=False)



# Coding nominal data 

#Define a generic function using Pandas replace function
def coding(col, codeDict):
  colCoded = pd.Series(col, copy=True)
  for key, value in codeDict.items():
    colCoded.replace(key, value, inplace=True)
  return colCoded
 
#Coding LoanStatus as Y=1, N=0:
print 'Before Coding:'
print pd.value_counts(data["Loan_Status"])
data["Loan_Status_Coded"] = coding(data["Loan_Status"], {'N':0,'Y':1})
print '\nAfter Coding:'
print pd.value_counts(data["Loan_Status_Coded"])



#Iterating over row of a dataframe changing types 

#Iterate through each row and assign variable type.
#Note: astype is used to assign types

for i, row in colTypes.iterrows():  #i: dataframe index; row: each row in series format
    if row['type']=="categorical":
        data[row['feature']]=data[row['feature']].astype(np.object)
    elif row['type']=="continuous":
        data[row['feature']]=data[row['feature']].astype(np.float)
print data.dtypes


#source: https://www.analyticsvidhya.com/blog/2016/01/12-pandas-techniques-python-data-manipulation/