Merge branch 'master' of https://gitlab.cl.uni-heidelberg.de/vdberg/webis_bias_flipper_2018

    except KeyError:

        return None

def load_nameslab():

    namfn = 'data/names_labeled.csv'

    df = pd.read_csv(namfn, index_col=0)

    df = df.replace({'l': 'Left', 'r': 'Right', 'c':'Center'})

    return df, df.name_bias.to_dict()

df = read_csvs('outputs') #pd.read_csv('vdberg_output.csv')

pd.set_option('display.max_colwidth', 200)

pd.set_option('display.max_columns', 10)

df = pd.read_csv('data/srl_output.csv', names=['name','verb','arg','same','sent_id']) #read_csvs('outputs') #pd.read_csv('vdberg_output.csv')

sent = pd.read_csv('data/sent_df.csv', names=['sent_id','bias','doc_id','s'])

df = pd.merge(df, sent, on=['sent_id'])

namlabs_df, namlabs = load_nameslab()

df = pd.merge(df, namlabs_df, on=['name'])

#df = df.drop(columns='same')

df = df[df['arg'].str.startswith('B-ARG0')]

print(df.columns)

print(df.shape)

#print(df.head(n=5))

#nltk.download('wordnet')

#lemmatizer = WordNetLemmatizer()

#df['lemma'] = df.verb.apply(lemmatizer.lemmatize)

df = df.replace({'From the Center': 'Center', 'From the Right': 'Right', 'From the Left': 'Left'})

df.verb = df.verb.str.lower()

overall_counts = df.verb.value_counts()

def test(v):

    return overall_counts[v] > 5

df = df[df.verb.apply(test)]

def cust(x):

    return ' (' + str(round(x, 2)) + ')'

grs = pd.DataFrame()

for n, gr in df.groupby(['bias', 'name_bias']):

    counts = gr.verb.value_counts()

    counts = counts / overall_counts.loc[counts.index]

    counts.index += counts.apply(cust)

    sorted_verbs = counts.sort_values(ascending=False).head(10)

    grs[n] = sorted_verbs.index

print(grs)

exit(0)

nltk.download('wordnet')

lemmatizer = WordNetLemmatizer()

df['lemma'] = df.verb.apply(lemmatizer.lemmatize)