1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
|
import sqlite3
import numpy as np
from sqlalchemy import create_engine
from pandas import (
DataFrame,
date_range,
read_sql_query,
read_sql_table,
)
from ..pandas_vb_common import tm
class SQL:
params = ["sqlalchemy", "sqlite"]
param_names = ["connection"]
def setup(self, connection):
N = 10000
con = {
"sqlalchemy": create_engine("sqlite:///:memory:"),
"sqlite": sqlite3.connect(":memory:"),
}
self.table_name = "test_type"
self.query_all = f"SELECT * FROM {self.table_name}"
self.con = con[connection]
self.df = DataFrame(
{
"float": np.random.randn(N),
"float_with_nan": np.random.randn(N),
"string": ["foo"] * N,
"bool": [True] * N,
"int": np.random.randint(0, N, size=N),
"datetime": date_range("2000-01-01", periods=N, freq="s"),
},
index=tm.makeStringIndex(N),
)
self.df.loc[1000:3000, "float_with_nan"] = np.nan
self.df["date"] = self.df["datetime"].dt.date
self.df["time"] = self.df["datetime"].dt.time
self.df["datetime_string"] = self.df["datetime"].astype(str)
self.df.to_sql(self.table_name, self.con, if_exists="replace")
def time_to_sql_dataframe(self, connection):
self.df.to_sql("test1", self.con, if_exists="replace")
def time_read_sql_query(self, connection):
read_sql_query(self.query_all, self.con)
class WriteSQLDtypes:
params = (
["sqlalchemy", "sqlite"],
[
"float",
"float_with_nan",
"string",
"bool",
"int",
"date",
"time",
"datetime",
],
)
param_names = ["connection", "dtype"]
def setup(self, connection, dtype):
N = 10000
con = {
"sqlalchemy": create_engine("sqlite:///:memory:"),
"sqlite": sqlite3.connect(":memory:"),
}
self.table_name = "test_type"
self.query_col = f"SELECT {dtype} FROM {self.table_name}"
self.con = con[connection]
self.df = DataFrame(
{
"float": np.random.randn(N),
"float_with_nan": np.random.randn(N),
"string": ["foo"] * N,
"bool": [True] * N,
"int": np.random.randint(0, N, size=N),
"datetime": date_range("2000-01-01", periods=N, freq="s"),
},
index=tm.makeStringIndex(N),
)
self.df.loc[1000:3000, "float_with_nan"] = np.nan
self.df["date"] = self.df["datetime"].dt.date
self.df["time"] = self.df["datetime"].dt.time
self.df["datetime_string"] = self.df["datetime"].astype(str)
self.df.to_sql(self.table_name, self.con, if_exists="replace")
def time_to_sql_dataframe_column(self, connection, dtype):
self.df[[dtype]].to_sql("test1", self.con, if_exists="replace")
def time_read_sql_query_select_column(self, connection, dtype):
read_sql_query(self.query_col, self.con)
class ReadSQLTable:
def setup(self):
N = 10000
self.table_name = "test"
self.con = create_engine("sqlite:///:memory:")
self.df = DataFrame(
{
"float": np.random.randn(N),
"float_with_nan": np.random.randn(N),
"string": ["foo"] * N,
"bool": [True] * N,
"int": np.random.randint(0, N, size=N),
"datetime": date_range("2000-01-01", periods=N, freq="s"),
},
index=tm.makeStringIndex(N),
)
self.df.loc[1000:3000, "float_with_nan"] = np.nan
self.df["date"] = self.df["datetime"].dt.date
self.df["time"] = self.df["datetime"].dt.time
self.df["datetime_string"] = self.df["datetime"].astype(str)
self.df.to_sql(self.table_name, self.con, if_exists="replace")
def time_read_sql_table_all(self):
read_sql_table(self.table_name, self.con)
def time_read_sql_table_parse_dates(self):
read_sql_table(
self.table_name,
self.con,
columns=["datetime_string"],
parse_dates=["datetime_string"],
)
class ReadSQLTableDtypes:
params = [
"float",
"float_with_nan",
"string",
"bool",
"int",
"date",
"time",
"datetime",
]
param_names = ["dtype"]
def setup(self, dtype):
N = 10000
self.table_name = "test"
self.con = create_engine("sqlite:///:memory:")
self.df = DataFrame(
{
"float": np.random.randn(N),
"float_with_nan": np.random.randn(N),
"string": ["foo"] * N,
"bool": [True] * N,
"int": np.random.randint(0, N, size=N),
"datetime": date_range("2000-01-01", periods=N, freq="s"),
},
index=tm.makeStringIndex(N),
)
self.df.loc[1000:3000, "float_with_nan"] = np.nan
self.df["date"] = self.df["datetime"].dt.date
self.df["time"] = self.df["datetime"].dt.time
self.df["datetime_string"] = self.df["datetime"].astype(str)
self.df.to_sql(self.table_name, self.con, if_exists="replace")
def time_read_sql_table_column(self, dtype):
read_sql_table(self.table_name, self.con, columns=[dtype])
from ..pandas_vb_common import setup # noqa: F401 isort:skip
|
