import pandas as pd
df = pd.read_csv("test.scv")
df.tail(3)
df.columns = [c.lower() for c in df.columns]
df = df.rename(columns={'p': 'points',
'gp': 'games',
'sot': 'shots_on_target',
'g': 'goals',
'ppg': 'points_per_game',
'a': 'assists',})
df['salary'] = df['salary'].apply(lambda x: x.strip('$m'))
df['team'] = pd.Series('', index=df.index)
df.insert(loc=8, column='position', value='')
def process_player_col(text):
name, rest = text.split('\n')
position, team = [x.strip() for x in rest.split(' — ')]
return pd.Series([name, team, position])
df[['player', 'team', 'position']] = df.player.apply(process_player_col)
for idx,row in df.iterrows():
name, position, team = process_player_col(row['player'])
df.ix[idx, 'player'], df.ix[idx, 'position'], df.ix[idx, 'team'] = name, position, team
cols = ['player', 'position', 'team']
df[cols] = df[cols].applymap(lambda x: x.lower())
nans = df.shape[0] - df.dropna().shape[0]
print('%d rows have missing values' % nans)
df[df['assists'].isnull()]
df[df['assists'].notnull()]
df.fillna(value=0, inplace=True)
import numpy as np
df = df.append(pd.Series(
[np.nan]*len(df.columns),
index=df.columns),
ignore_index=True)
df.loc[df.index[-1], 'player'] = 'new player'
df.loc[df.index[-1], 'salary'] = 12.3
df.sort('goals', ascending=False, inplace=True)
df.index = range(1,len(df.index)+1)
df_2 = df.copy()
df_2.loc[0:2, 'salary'] = [20.0, 15.0]
df.set_index('player', inplace=True)
df_2.set_index('player', inplace=True)
df.update(other=df_2['salary'], overwrite=True)
df.reset_index(inplace=True)
df[ (df['team'] == 'arsenal') | (df['team'] == 'chelsea') ]
df[ (df['team'] == 'arsenal') & (df['position'] == 'forward') ]
types = df.columns.to_series().groupby(df.dtypes).groups
df.loc[:, (df.dtypes == np.dtype('O')).values].head()
df['salary'] = df['salary'].astype(float)