def calculate_TSNE(self,
indecies=None,
sample=5000,
n_jobs=1,
multicore=False,
**kwargs):
"""
Calculate the TSNE and store it in the h5 object
Args:
indecies (list): select a subset based on indecies
sample (int): number of cells to downsample to if None use them all
n_jobs (int): number of cpus to use (if multicore is True)
multicore (bool): use the MultiCoreTSNE package
**kwargs: pass any other arguments to TSNE
"""
if not self.mode in ['w', 'r+', 'a']:
raise ValueError('cant write for readonly')
dsdata = self.fractions.copy()
if indecies is not None:
dsdata = dsdata.loc[indecies]
if sample is not None:
if dsdata.shape[0] < sample: sample = dsdata.shape[0]
dsdata = dsdata.sample(n=sample)
if self.verbose:
sys.stderr.write("executing TSNE decomposition on " +
str(dsdata.shape[0]) + " cells\n")
tsne = None
if multicore:
from MulticoreTSNE import MulticoreTSNE as mTSNE
if self.verbose: sys.stderr.write("Using MulticoreTSNE\n")
tsne = mTSNE(n_jobs=n_jobs, **kwargs).fit_transform(dsdata)
else:
if self.verbose: sys.stderr.write("Using sklearn TSNE\n")
tsne = TSNE(**kwargs).fit_transform(dsdata)
tsne = pd.DataFrame(tsne, columns=['x', 'y'])
tsne.index = dsdata.index
tsne = tsne.reset_index().merge(
self.clusters.reset_index()[['cluster_id', 'k', 'db_id'] +
self.groupby],
on=['db_id'])
tsne['cluster_name'] = tsne['cluster_id'].astype(str)
self.tsne = tsne
"Off-Target", "Blocked", "Corners", "Offsides", "Free Kicks", \
"Saves", "Pass Accuracy %", "Passes", "Distance Covered (Kms)", \
"Fouls Committed", "Yellow Card", "Yellow & Red", "Red"] # , "1st Goal"
names = ["Goal Scored", "On-Target", "Off-Target", "Ball Possession %", \
"Fouls Committed"]
data_file_name = "../data/FIFA_2018_Statistics.csv"
df = pd.read_csv(data_file_name)
df = df[names]
df_norm = (df - df.mean()) / (df.max() - df.min())
print(df_norm)
input_data_mat = np.array(df_norm)
df_embedded = TSNE(n_components=2).fit_transform(df_norm)
# pca = PCA(n_components=2)
# df_embedded = pca.fit(input_data_mat).transform(input_data_mat)
print(df_embedded)
df_embedded = pd.DataFrame(df_embedded)
df_embedded.reset_index(inplace=True)
df_embedded = df_embedded.rename(columns={0: "x", 1: "y"})
print(df_embedded)
df_embedded.to_csv("../data/tsne-results.csv", index=0)
