Beispiel #1
0
 def setup(self, N):
     df = self.df = vaex.open(generate_numerical())[:N]
     df['id1'] = df['i1_100']
     df['id2'] = df['i1_100']
     df['id3'] = df['i4_1M']
     df['id4'] = df['i1_100']
     df['id5'] = df['i1_100']
     df['id6'] = df['i4_1M']
     df['v1'] = df['i1_10']
     df['v2'] = df['i1_10']
     df['v3'] = df['x4']
Beispiel #2
0
    def setup(self, N):
        self.df = vaex.open(generate_numerical())[:N]
        self.df.categorize(self.df.i8_10, min_value=5, max_value=15, inplace=True)
        self.df.categorize(self.df.i4_10, min_value=5, max_value=15, inplace=True)
        self.df.categorize(self.df.i2_10, min_value=5, max_value=15, inplace=True)
        self.df.categorize(self.df.i1_10, min_value=5, max_value=15, inplace=True)

        self.df.categorize(self.df.i8_1K, min_value=5, max_value=1_000+5, inplace=True)
        self.df.categorize(self.df.i4_1K, min_value=5, max_value=1_000+5, inplace=True)
        self.df.categorize(self.df.i2_1K, min_value=5, max_value=1_000+5, inplace=True)
        # self.df.categorize(self.df.i1_1K, min_value=5, max_value=1_000+5)

        self.df.categorize(self.df.i8_1M, min_value=5, max_value=1_000_000+5, inplace=True)
        self.df.categorize(self.df.i4_1M, min_value=5, max_value=1_000_000+5, inplace=True)
Beispiel #3
0
def time_sort_ints(N, T):
    df = vaex.open(generate_numerical())
    df = df[:N]
    df.sort(f'i8_{T}')
Beispiel #4
0
 def setup(self, N):
     self.df = vaex.open(generate_numerical())[:N]
     self.df['i4_1M_POT'] = self.df['i4_1M'] * 2**8
     self.dff = self.df[(self.df.x > 0) & (self.df.y < 0)]
     len(self.dff)  # fill cache
Beispiel #5
0
 def setup_cache(self):
     # ensure the dataframe is generated
     generate_numerical()
Beispiel #6
0
 def setup(self, N):
     self.df = vaex.open(generate_numerical())[:N]
     self.df['i4_1M_POT'] = self.df['i4_1M'] * 2**8
Beispiel #7
0
 def setup(self, N):
     self.df = vaex.open(generate_numerical())[:N]
     self.df.categorize(self.df.i8_10, list(range(5, 15)), check=False)
     self.df.categorize(self.df.i4_10, list(range(5, 15)), check=False)
     self.df.categorize(self.df.i2_10, list(range(5, 15)), check=False)
     self.df.categorize(self.df.i1_10, list(range(5, 15)), check=False)
Beispiel #8
0
 def setup(self, N, M):
     self.df_num = vaex.open(generate_numerical())[:N]
     self.df_str = vaex.open(generate_strings())[:N]
Beispiel #9
0
 def setup_cache(self):
     generate_numerical()
     generate_strings()