def invalue_to_similarity(invalue_df, orientation_df):
"""
invalue_df: converted DataFrame of user inputs
orientation_df: DataFrame of all people of that orientation
"""
# concat input values to orientation df to prep for cosine similarity
df = pd.concat([orientation_df, invalue_df])
# ohe
df_encoded = OneHotEncoder(use_cat_names=True).fit_transform(df)
# make cosine_similarity input (input X)
cosine_input = pd.DataFrame(df_encoded.iloc[-1]).T
# drop last encoded row (input Y -- data for input X to reference)
df_encoded.drop(df_encoded.tail(1).index, inplace=True)
# cosine_similarity(X, y)
similarity = cosine_similarity(cosine_input, df_encoded)
# return top 5 matches
top5 = pd.DataFrame(similarity.tolist()[0],
columns=['similarity'],
index=df_encoded.index).sort_values(
by='similarity', ascending=False).iloc[:5]
# return top 5 matches in a df with cosine similarities
results = pd.DataFrame(columns=cupid.columns)
for i in top5.index:
results = results.append(pd.DataFrame(cupid.loc[i]).T)
return results
def train_test_split(dataset, categorical_cols, train_fraction):
"""
Splits the dataset into a train and a test set
:param dataset: data to be split
:param categorical_cols: list of the column names of the categorical columns (previously identified automatically)
:param train_fraction: portion of dataset to be used as train set
:return: a list [train set, one-hot-encoded train set, test set, one-hot-encoded test set]
"""
dataset_encoded = OneHotEncoder(cols=categorical_cols,
use_cat_names=True).fit_transform(dataset)
train_len = int(len(dataset.index) * train_fraction)
train_set = dataset.sample(n=train_len, random_state=1)
train_set_encoded = dataset_encoded.loc[train_set.index].reset_index(
drop=True)
test_set = dataset.drop(train_set.index).reset_index(drop=True)
test_set_encoded = dataset_encoded.drop(
train_set.index).reset_index(drop=True)
return train_set.reset_index(
drop=True), train_set_encoded, test_set, test_set_encoded
def train_test_split(dataset, train_fraction):
"""
Splits the dataset into a train and a test set
:param dataset: data to be split
:param categorical_cols: list of the column names of the categorical columns (previously identified automatically)
:param train_fraction: portion of dataset to be used as train set
:return: a list [train set, one-hot-encoded train set, test set, one-hot-encoded test set]
"""
#### Default - set string values as categorial except target column ####
##########################################################################
categorical_cols = []
for (columnName, columnData) in dataset.iteritems():
for value in columnData.values:
if type(value) is str:
categorical_cols.append(columnName)
break
if (categorical_cols[-1] == "CLASS"):
categorical_cols = np.delete(categorical_cols, -1)
## AR: improve categorial selction
dataset_encoded = OneHotEncoder(cols=categorical_cols,
use_cat_names=True).fit_transform(dataset)
if (train_fraction == 1):
return dataset_encoded, dataset_encoded, dataset_encoded, dataset_encoded
train_len = int(len(dataset.index) * train_fraction)
train_set = dataset.sample(n=train_len, random_state=1)
train_set_encoded = dataset_encoded.loc[train_set.index].reset_index(
drop=True)
test_set = dataset.drop(train_set.index).reset_index(drop=True)
test_set_encoded = dataset_encoded.drop(
train_set.index).reset_index(drop=True)
return train_set.reset_index(
drop=True), train_set_encoded, test_set, test_set_encoded
