analyticsindiamagazine

# LINEAR CLASSIFIER

# Set the number of training steps
num_steps = 1500

# A logger for logging the training data
tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.DEBUG)

# Defining the classifier
classifier = tf.estimator.LinearClassifier(

analyticsindiamagazine

# Convert dataset to tf.Example protos
examples = df_to_examples(df)

#Create feature spec for the data
feature_spec = create_feature_spec(df, features_and_labels)

#Creating input features from training set 
train_inpf = functools.partial(tfexamples_input_fn, examples, feature_spec, label_column)

analyticsindiamagazine

# Specify the dataframe
df = train

# Setting the categorical feature to predict or classify (Target)
label_column = 'Delivery_Time'

#List the uique classes in the target column
classes = list(df[label_column].unique())

#Encode the categories in the target column using the unique classes

analyticsindiamagazine

# Creates a tf feature spec from the dataframe and columns specified.
def create_feature_spec(df, columns=None):
    feature_spec = {}
    if columns == None:
        columns = df.columns.values.tolist()
    for f in columns:
        if df[f].dtype is np.dtype(np.int64):
            feature_spec[f] = tf.compat.v1.FixedLenFeature(shape=(), dtype=tf.int64)
        elif df[f].dtype is np.dtype(np.float64):
            feature_spec[f] = tf.compat.v1.FixedLenFeature(shape=(), dtype=tf.float32)

analyticsindiamagazine

#Importing tensorflow 2
try:
  %tensorflow_version 2.x  #gpu
except Exception:
  pass
import tensorflow as tf

#Installing the What-If Tool widget 
try:
  !pip install --upgrade witwidget

analyticsindiamagazine

#Splitting training set into training and validation sets
from sklearn.model_selection import train_test_split
train, val = train_test_split(train_sample, test_size = 0.1, random_state = 123)

#Seperating the independent and dependent variables
cols = [list of column names in order] #last column corresponds to y or target variable
#Training set
X_train = train[cols[:-1]]
Y_train = train[cols[-1]]
#Validation set

analyticsindiamagazine

#Filling Nulls/Nans
train.fillna('NAN', inplace = True)

#Label Encoding
from sklearn.preprocessing import LabelEncoder
le_c = LabelEncoder().fit(unique_cuisines)
train['Cuisines'] = le_l.transform(train['Cuisines'])

#Scaling
cols = [list of columns to apply standard scaler]

analyticsindiamagazine

#A function to find all the non numeric values
def non_numerals(series):
  non_numerals = []
  for i in series.unique():
    try :
      i = float(i)
    except:
      non_numerals.append(i)
  return non_numerals

analyticsindiamagazine

#A function to find the maximun number of features in a single cell
def max_features_in_single_row(train, test, delimiter):
  max_info = 0 
  item_lis = list(train.append(test))
  for i in item_lis:
    if len(i.split("{}".format(delimiter))) > max_info:
      max_info = len(i.split("{}".format(delimiter)))
  print("\n","-"*35)    
  print("Max_Features in One Observation = ", max_info)
  return max_info

analyticsindiamagazine

#Loading Data
train = pd.read_excel("/GD/.../DataSets/Data_Train.xlsx")

#display the dataframe head(10) returns the first 10 rows
train.head(10)

#Shape of a table (number or rows, number of columns)
train.shape

#Display the names of all columns in a dataframe