Esempi in Python per add_missing_indicator

Esempio n. 1

File: score.py Progetto: quezadasubiabre/DeploymentMachineLeatning

def predict(data):

    # extract first letter from cabin

    pf.extract_cabin_letter(data, 'cabin')

    # impute NA categorical
    for var in ['age', 'fare']:
        pf.add_missing_indicator(data, var)

    # impute NA numerical

    for var in config.CATEGORICAL_VARS:
        pf.impute_na(data, var)

    # Group rare labels
    for var in config.CATEGORICAL_VARS:
        pf.remove_rare_labels(data, var, config.FREQUENT_LABELS)

    # encode variables
    data = pf.encode_categorical(df, config.CATEGORICAL_VARS)

    # scale variables

    data = pf.scale_features(data, config.OUTPUT_SCALER_PATH)

    # make predictions
    predictions, _ = pf.predict(data, config.OUTPUT_MODEL_PATH)

    return predictions

Esempio n. 2

File: score.py Progetto: annplaube/mldeploy

def predict(data):

    # extract first letter from cabin
    pf.extract_cabin_letter(data, 'cabin')

    # impute NA numerical
    for var in config.NUMERICAL_TO_IMPUTE:
        pf.add_missing_indicator(data, var)
        pf.impute_na(data, var, config.IMPUTATION_DICT[var])

    # impute NA categorical
    for var in config.CATEGORICAL_VARS:
        pf.impute_na(data, var)

    # Group rare labels
    for var, labels in config.FREQUENT_LABELS.items():
        pf.remove_rare_labels(data, var, labels)

    # encode variables
    for var in config.CATEGORICAL_VARS:
        data = pf.encode_categorical(data, var)

    # check all dummies were added
    pf.check_dummy_variables(data, config.DUMMY_VARIABLES)

    data = data[config.ALL_VARS]

    # scale variables
    data = pf.scale_features(data, config.OUTPUT_SCALER_PATH)

    # make predictions
    predictions = pf.predict(data, config.OUTPUT_MODEL_PATH)

    return predictions

Esempio n. 3

File: score.py Progetto: wonglimey/machine-learning-pipeline

def predict(data):

    # extract first letter from cabin
    data[config.EXTRACT_VARIABLE] = pf.extract_cabin_letter(
        data, config.EXTRACT_VARIABLE)

    # impute NA categorical
    for var in config.CATEGORICAL_TO_ENCODE:
        data[var] = pf.impute_na(data, var, replacement='Missing')

    # impute NA numerical
    for var in config.NUMERICAL_TO_IMPUTE:
        if (var == 'age'):
            data[var] = pf.add_missing_indicator(data, var, config.AGE_MEDIAN)
        else:
            data[var] = pf.add_missing_indicator(data, var, config.FARE_MEDIAN)

    # Group rare labels
    for var in config.CATEGORICAL_TO_ENCODE:
        data[var] = pf.remove_rare_labels(data, var, config.RARE_VALUE)

    # encode variables
    for var in config.CATEGORICAL_TO_ENCODE:
        data = pf.encode_categorical(data, var)

    # check all dummies were added
    pf.check_dummy_variables(data, config.DUMMY_VARIABLE)

    # scale variables
    data = pf.scale_features(data[config.FEATURES], config.OUTPUT_SCALER_PATH)

    # make predictions
    predictions = pf.predict(data, config.OUTPUT_MODEL_PATH)

    return predictions

Esempio n. 4

File: score.py Progetto: hurshd0/deploying-machine-learning-models

def predict(data):
    # impute categorical variables
    for var in config.CATEGORICAL_VARS:
        data[var] = pf.impute_na(data, var, replacement='Missing')

    # impute numerical variables
    for var in config.NUMERICAL_TO_IMPUTE:

        # add missing indicator first
        data[var + '_na'] = pf.add_missing_indicator(data, var)

        # impute NA
        data[var] = pf.impute_na(data, var,
                                 replacement=config.IMPUTATION_DICT[var])

    # Group rare labels
    for var in config.CATEGORICAL_VARS:
        data[var] = pf.remove_rare_labels(data, var,
                                          config.FREQUENT_LABELS[var])
    # encode categorical variables
    for var in config.CATEGORICAL_VARS:
        data = pf.encode_categorical(data, var)

    # check all dummies were added
    data = pf.check_dummy_variables(data, config.DUMMY_VARIABLES)

    # scale variables
    scaler = pf.scale_features(data,
                               config.OUTPUT_SCALER_PATH)
    # make predictions
    predictions = pf.predict(data, config.OUTPUT_MODEL_PATH)

    return predictions

Esempio n. 5

File: score.py Progetto: overdrivek/MLDeployment

def predict(data):
    
    # extract first letter from cabin
    X_test = pf.extract_cabin_letter(data, config.IMPUTATION_DICT['cabin_variable'])

    # impute NA categorical
    X_test = pf.add_missing_indicator(X_test, config.CATEGORICAL_VARS)
    
    
    # impute NA numerical
    for var in config.NUMERICAL_TO_IMPUTE:
        X_test = pf.impute_na(X_test,var,replace_by=config.IMPUTATION_DICT[var], add_na_columns=True)

    
    # Group rare labels
    X_test = pf.remove_rare_labels(X_test, config.FREQUENT_LABELS)
    
    # encode variables
    for var in config.CATEGORICAL_VARS:
        X_test = pf.encode_categorical(X_test, var)
    X_test.drop(labels=config.CATEGORICAL_VARS, axis=1, inplace=True)
        
    # check all dummies were added
    X_test = pf.check_dummy_variables(X_test, config.DUMMY_VARIABLES)

    
    # scale variables
    X_test = pf.scale_features(X_test, config.OUTPUT_SCALER_PATH)
    
    # make predictions
    predictions = pf.predict(X_test,config.OUTPUT_MODEL_PATH)

    
    return predictions

Esempio n. 6

File: score.py Progetto: furkangnr/dmlm-research-and-production

def predict(data):

    # extract first letter from cabin
    data["cabin"] = pf.extract_cabin_letter(data, "cabin")

    # impute NA categorical
    for var in config.CATEGORICAL_VARS:
        data[var] = pf.impute_na(data, var, replacement="Missing")

    # impute NA numerical
    for var in config.NUMERICAL_TO_IMPUTE:
        data[var + '_NA'] = pf.add_missing_indicator(data, var)
        data[var] = pf.impute_na(data,
                                 var,
                                 replacement=config.IMPUTATION_DICT[var])

    # Group rare labels
    for var in config.CATEGORICAL_VARS:
        data[var] = pf.remove_rare_labels(data, var,
                                          config.FREQUENT_LABELS[var])

    # encode variables
    for var in config.CATEGORICAL_VARS:
        data = pf.encode_categorical(data, var)

    # check all dummies were added
    data = pf.check_dummy_variables(data, config.DUMMY_VARIABLES)

    # scale variables
    data = pf.scale_features(data, config.OUTPUT_SCALER_PATH)

    # make predictions
    predictions = pf.predict(data, config.OUTPUT_MODEL_PATH)

    return predictions

Esempio n. 7

def predict(data):

    data = pf.load_data(config.PATH_TO_DATASET)

    X_train, X_test, y_train, y_test = pf.divide_train_test(data, config.TARGET)
    data = X_test.copy()

        # impute categorical variables
    data = pf.add_missing_indicator(data, config.CATEGORICAL_VARS)

    # extract first letter from cabin
    data = pf.extract_cabin_letter(data, 'cabin')

    # impute NA categorical
    data = pf.impute_na(data, config.CATEGORICAL_VARS)

    # impute NA numerical
    data = pf.add_missing_indicator(data, config.NUMERICAL_TO_IMPUTE)
    data = pf.impute_num(data, config.NUMERICAL_TO_IMPUTE)

    # Group rare labels
    data = pf.remove_rare_labels(data, config.CATEGORICAL_VARS)

    # encode variables
    data, data_features = pf.encode_categorical(data, config.CATEGORICAL_VARS)

    print(data.head(1))
    
    # check all dummies were added
    data = pf.check_dummy_variables(data, config.DUMMY_VARIABLES)
    
    # scale variables
    data = pf.scale_features(data, config.OUTPUT_SCALER_PATH)

    # make predictions
    class_, pred = pf.predict(data, config.OUTPUT_MODEL_PATH)

    
    return class_

Esempio n. 8

def predict(data):
    # extract first letter from cabin
    data['cabin'] = pf.extract_cabin_letter(data, 'cabin')

    # impute NA categorical
    for var in config.CATEGORICAL_VARS:
        data[var] = pf.impute_na(data, var, value='Missing')

    # impute NA numerical
    for var in config.NUMERICAL_TO_IMPUTE:
        # add missing indicator
        pf.add_missing_indicator(data, var)

        # replace NaN by median
        median_val = data[var].median()
        data[var] = pf.impute_na(data, var, value=median_val)

    # Group rare labels
    for var in config.CATEGORICAL_VARS:
        data[var] = pf.remove_rare_labels(data, var,
                                          config.FREQUENT_LABELS[var])

    # encode variables
    for var in config.CATEGORICAL_VARS:
        data = pf.encode_categorical(data, var)

    # check all dummies were added
    for var in config.CATEGORICAL_VARS:
        pf.check_dummy_variables(data, config.DUMMY_VARIABLES[var])

    # scale variables
    data = pf.scale_features(data, config.OUTPUT_SCALER_PATH)

    # make predictions
    predictions = pf.predict(data, config.OUTPUT_MODEL_PATH)

    return predictions

Esempio n. 9

def predict(data):
    
    # extract first letter from cabin
    data = pf.extract_cabin_letter(data, 'cabin')


    # impute NA categorical
    for var in config.CATEGORICAL_VARS:
        data = pf.impute_na(data, var, config.IMPUTATION_DICT)    
    
    # impute NA numerical
    for var in ['age', 'fare']:
        data = pf.impute_na(data, var, config.IMPUTATION_DICT)
    
    # add indicator variables
    for var in ['age', 'fare']:
        data = pf.add_missing_indicator(data, var)
    
    
    # Group rare labels
    for var in config.CATEGORICAL_VARS:
        data = pf.remove_rare_labels(data, config.FREQUENT_LABELS, var)
    
    # encode variables
    for var in config.CATEGORICAL_VARS:
        data = pf.encode_categorical(data, var)
        
        
    # check all dummies were added
    data = pf.check_dummy_variables(data, config.DUMMY_VARIABLES)

    
    # scale variables
    data = pf.scale_features(data, config.ORDERED_COLUMNS, config.OUTPUT_SCALER_PATH)

    
    # make predictions
    predictions = pf.predict(data, config.ORDERED_COLUMNS, config.OUTPUT_MODEL_PATH)

    
    return predictions

Esempio n. 10

File: score.py Progetto: AlexSkrn/Predicting-Survival-Titanic-ProcProgAssignment

def predict(data):

    # extract first letter from cabin
    data['cabin'] = pf.extract_cabin_letter(data, 'cabin')

    # impute NA categorical
    for var in config.CATEGORICAL_VARS:
        data[var] = pf.impute_na(data, var, replacement='Missing')

    # impute NA numerical
    for var in config.NUMERICAL_TO_IMPUTE:
        data[var] = pf.add_missing_indicator(data, var)
        data[var] = pf.impute_na(data, var, config.IMPUTATION_DICT[var])

    # Group rare labels
    for var in config.CATEGORICAL_VARS:
        data[var] = pf.remove_rare_labels(data, var,
                                          config.FREQUENT_LABELS[var])

    # encode variables
    data = pf.encode_categorical(data, config.CATEGORICAL_VARS)

    # check all dummies were added
    # print(data.shape)
    # print(data.columns)
    data = pf.check_dummy_variables(data, config.DUMMY_VARIABLES)
    # print(data.columns)
    # print(data.shape)
    data = data[config.FEATURES]

    # scale variables
    data = pf.scale_features(data, config.OUTPUT_SCALER_PATH)

    # print('test data shape', data.shape)
    # make predictions
    predictions = pf.predict(data, config.OUTPUT_MODEL_PATH)

    return predictions

Esempio n. 11

File: train.py Progetto: overdrivek/MLDeployment

df_data = pf.load_data(config.PATH_TO_DATASET)
df_target = df_data[config.TARGET]
df_data = df_data.drop([config.TARGET], axis=1)

# divide data set
X_train, X_test, y_train, y_test = pf.divide_train_test(
    df_data, df_target, seed=config.GLOBAL_SEED)

# get first letter from cabin variable
X_train = pf.extract_cabin_letter(X_train,
                                  config.IMPUTATION_DICT['cabin_variable'])
X_test = pf.extract_cabin_letter(X_test,
                                 config.IMPUTATION_DICT['cabin_variable'])

# impute categorical variables
X_train = pf.add_missing_indicator(X_train, config.CATEGORICAL_VARS)
X_test = pf.add_missing_indicator(X_test, config.CATEGORICAL_VARS)

# impute numerical variable
for var in config.NUMERICAL_TO_IMPUTE:
    X_train = pf.impute_na(X_train,
                           var,
                           replace_by=config.IMPUTATION_DICT[var],
                           add_na_columns=True)
    X_test = pf.impute_na(X_test,
                          var,
                          replace_by=config.IMPUTATION_DICT[var],
                          add_na_columns=True)

# Group rare labels
X_train = pf.remove_rare_labels(X_train, config.FREQUENT_LABELS)

Esempio n. 12

# ================================================
# TRAINING STEP - IMPORTANT TO PERPETUATE THE MODEL

# Load data
data = pf.load_data(config.PATH_TO_DATASET)

# divide data set
X_train, X_test, y_train, y_test = pf.divide_train_test(data, config.TARGET)

# get first letter from cabin variable
X_train['cabin'] = pf.extract_cabin_letter(X_train, 'cabin')
X_test['cabin'] = pf.extract_cabin_letter(X_test, 'cabin')

# impute categorical variables
for var in config.CATEGORICAL_VARS:
    X_train[var + '_na'] = pf.add_missing_indicator(X_train, var)
    X_train[var] = pf.impute_na(X_train, var)

    X_test[var + '_na'] = pf.add_missing_indicator(X_test, var)
    X_test[var] = pf.impute_na(X_test, var)

# impute numerical variable
for var in config.NUMERICAL_TO_IMPUTE:
    X_train[var + '_na'] = pf.add_missing_indicator(X_train, var)
    X_train[var] = pf.impute_na(X_train, var, config.IMPUTATION_DICT[var])
    X_test[var + '_na'] = pf.add_missing_indicator(X_test, var)
    X_test[var] = pf.impute_na(X_test, var, config.IMPUTATION_DICT[var])

# Group rare labels
for var in config.CATEGORICAL_VARS:
    X_train[var] = pf.remove_rare_labels(X_train, var,

Esempio n. 13

File: train.py Progetto: gonzalo71/TestGit

# divide data set

X_train, X_test, y_train, y_test = pf.divide_train_test(df, config.TARGET)

# get first letter from cabin variable
X_train['cabin'] = pf.extract_cabin_letter(X_train, 'cabin')

# impute categorical variables
for var in config.CATEGORICAL_VARS:
    X_train[var] = pf.impute_na(X_train, var)

# impute numerical variable
for var in config.NUMERICAL_TO_IMPUTE:

    # add missing indicator
    X_train[var + '_NA'] = pf.add_missing_indicator(X_train, var)

    # replace NaN by median
    X_train[var] = pf.impute_na(X_train,
                                var,
                                replacement=config.IMPUTATION_DICT[var])

# Group rare labels
for var in config.CATEGORICAL_VARS:
    X_train[var] = pf.remove_rare_labels(X_train, var,
                                         config.FREQUENT_LABELS[var])

# encode categorical variables
for var in config.CATEGORICAL_VARS:
    X_train = pf.encode_categorical(X_train, var)

Esempio n. 14

data = pf.load_data(config.PATH_TO_DATASET)

# divide data set
X_train, X_test, y_train, y_test = pf.divide_train_test(data, config.TARGET)

# get first letter from cabin variable
X_train['cabin'] = pf.extract_cabin_letter(X_train, 'cabin')

# impute categorical variables
for var in config.CATEGORICAL_VARS:
    X_train[var] = pf.impute_na(X_train, var, value='Missing')

# impute numerical variable
for var in config.NUMERICAL_TO_IMPUTE:
    # add missing indicator
    pf.add_missing_indicator(X_train, var)

    # replace NaN by median
    median_val = X_train[var].median()
    X_train[var] = pf.impute_na(X_train, var, value=median_val)

# Group rare labels
for var in config.CATEGORICAL_VARS:
    X_train[var] = pf.remove_rare_labels(X_train, var,
                                         config.FREQUENT_LABELS[var])

# encode categorical variables
for var in config.CATEGORICAL_VARS:
    X_train = pf.encode_categorical(X_train, var)

# check all dummies were added

Esempio n. 15

File: train.py Progetto: wonglimey/machine-learning-pipeline

X_train, X_test, y_train, y_test = pf.divide_train_test(data, config.TARGET)


# get first letter from cabin variable
X_train[config.EXTRACT_VARIABLE] = pf.extract_cabin_letter(X_train, config.EXTRACT_VARIABLE)


# impute categorical variables
for var in config.CATEGORICAL_TO_ENCODE:
    X_train[var] = pf.impute_na(X_train, var, replacement='Missing')


# impute numerical variable
for var in config.NUMERICAL_TO_IMPUTE:
    if (var == 'age'):
        X_train[var] = pf.add_missing_indicator(X_train, var, config.AGE_MEDIAN)
    else:
        X_train[var] = pf.add_missing_indicator(X_train, var, config.FARE_MEDIAN)


# Group rare labels
for var in config.CATEGORICAL_TO_ENCODE:
    X_train[var] = pf.remove_rare_labels(X_train, var, config.RARE_VALUE)


# encode categorical variables
for var in config.CATEGORICAL_TO_ENCODE:
    X_train = pf.encode_categorical(X_train, var)


# check all dummies were added

Esempio n. 16

import config

# ================================================
# TRAINING STEP - IMPORTANT TO PERPETUATE THE MODEL

# Load data
df = pf.load_data(config.PATH_TO_DATASET)

# divide data set
X_train, X_test, y_train, y_test = pf.divide_train_test(df, config.TARGET)

# get first letter from cabin variable
X_train = pf.extract_cabin_letter(X_train, 'cabin')

# impute categorical variables
X_train = pf.add_missing_indicator(X_train, config.CATEGORICAL_VARS)
X_train = pf.impute_na(X_train, config.CATEGORICAL_VARS)

# impute numerical variable
X_train = pf.add_missing_indicator(X_train, config.NUMERICAL_TO_IMPUTE)
X_train = pf.impute_num(X_train, config.NUMERICAL_TO_IMPUTE)

# Group rare labels
X_train = pf.remove_rare_labels(X_train, config.CATEGORICAL_VARS)

# encode categorical variables
X_train, X_train_features = pf.encode_categorical(X_train,
                                                  config.CATEGORICAL_VARS)

# check dummy variables
X_check

Esempio n. 17

File: train.py Progetto: rmania/ml_deployment

# divide data set
X_train, X_test, y_train, y_test = pf.divide_train_test(data, config.TARGET)

# get first letter from cabin variable
X_train['cabin'] = pf.extract_cabin_letter(df=X_train, var='cabin')
X_test['cabin'] = pf.extract_cabin_letter(df=X_test, var='cabin')

# impute categorical variables
for var in config.CATEGORICAL_VARS:
    X_train[var] = pf.impute_na(X_train, var, replacement='Missing')
    X_test[var] = pf.impute_na(X_test, var, replacement='Missing')

# impute numerical variable
for var in config.NUMERICAL_TO_IMPUTE:
    X_train[var] = pf.add_missing_indicator(df=X_train, var=var)
    X_test[var] = pf.add_missing_indicator(df=X_test, var=var)

# Group rare labels
for var in config.CATEGORICAL_VARS:
    X_train[var] = pf.remove_rare_labels(X_train, var,
                                         config.FREQUENT_LABELS[var])
    X_test[var] = pf.remove_rare_labels(X_test, var,
                                        config.FREQUENT_LABELS[var])

# encode categorical variables
X_train = pf.encode_categorical(df=X_train, var=config.CATEGORICAL_VARS)
X_test = pf.encode_categorical(df=X_test, var=config.CATEGORICAL_VARS)

# check all dummies were added
X_train = pf.check_dummy_variables(X_train, config.DUMMY_VARIABLES)

Esempio n. 18

File: train.py Progetto: nimecan/Deployment-of-ML-Models

data = pf.load_data(config.PATH_TO_DATASET)

# divide data set
X_train, X_test, y_train, y_test = pf.divide_train_test(data, config.TARGET)

# get first letter from cabin variable
X_train["cabin"] = pf.extract_cabin_letter(X_train, "cabin")
print(X_train["cabin"].unique())

# impute categorical variables
for var in config.CATEGORICAL_VARS:
    X_train[var] = pf.impute_na(X_train, var, replacement='Missing')

# impute numerical variable with median
for var in config.NUMERICAL_TO_IMPUTE:
    X_train[var + "_na"] = pf.add_missing_indicator(X_train, var)
    median_train_var = config.IMPUTATION_DICT[var]
    X_train[var] = pf.impute_na(X_train, var, replacement=median_train_var)

# Group rare labels
for var in config.CATEGORICAL_VARS:
    # Frequent labels found in Train set
    freq_labels = config.FREQUENT_LABELS[var]
    # Remove rare labels from both train and test set
    X_train[var] = pf.remove_rare_labels(X_train, var, freq_labels)

# encode categorical variables
for var in config.CATEGORICAL_VARS:
    X_train = pf.encode_categorical(X_train, var)

# check all dummies were added

Esempio n. 19

df = pf.load_data(config.PATH_TO_DATASET)

# divide data set
X_train, X_test, y_train, y_test = pf.divide_train_test(df, config.TARGET)

# get first letter from cabin variable
X_train = pf.extract_cabin_letter(X_train, 'cabin')
X_test = pf.extract_cabin_letter(X_test, 'cabin')

# impute categorical variables
X_train = pf.impute_na(X_train, config.CATEGORICAL_VARS)
X_test = pf.impute_na(X_test, config.CATEGORICAL_VARS)

# impute numerical variable
for var in config.IMPUTATION_DICT.keys():
    X_train = pf.add_missing_indicator(X_train, var)
    X_test = pf.add_missing_indicator(X_test, var)

    X_train = pf.impute_na(X_train, var, config.IMPUTATION_DICT[var])
    X_test = pf.impute_na(X_test, var, config.IMPUTATION_DICT[var])

# Group rare labels
for var in config.FREQUENT_LABELS.keys():
    X_train = pf.remove_rare_labels(X_train, var, config.FREQUENT_LABELS[var])
    X_test = pf.remove_rare_labels(X_test, var, config.FREQUENT_LABELS[var])

# encode categorical variables
for var in config.CATEGORICAL_VARS:
    X_train = pf.encode_categorical(X_train, var)
    X_test = pf.encode_categorical(X_test, var)