def test_case1():
df2 = df1.copy()
df2 = df1[~df1.isnull().any(axis=1)]
df2['Sex'] = df2['Sex'].map({'male': 0, 'female': 1})
checker = PatternSynthesizer(dispatch_gen(df1, "df1", 0, 0),
dispatch_gen(df2, "df2", 0, 1),
Info(None, None), [])
l = checker.check(df1, df2)
print("df1", "->", "df2", "\033[96m", checker.summary, "\033[0m")
def test_groupby():
df2 = df1.copy()
df2 = df2.groupby(['Name'])['Age'].sum()
df2 = df2.reset_index()
df2 = df2.sort_values('Age', ascending=False)
checker = PatternSynthesizer(dispatch_gen(df1, "df1", 0, 0),
dispatch_gen(df2, "df2", 0, 1),
Info(None, None), [])
l = checker.check(df1, df2)
print("df1", "->", "df2", "\033[96m", checker.summary, "\033[0m")
def test_double():
df2 = df1.copy()
df2.dropna(inplace=True)
checker = PatternSynthesizer(dispatch_gen(df1, "df1", 0, 0),
dispatch_gen(df2, "df2", 0, 1),
Info(None, None), [])
l = checker.check(df1, df2)
print("df1", "->", "df2", "\033[96m", checker.summary, "\033[0m")
l = checker.check(df1, df2)
print("df1", "->", "df2", "\033[96m", checker.summary, "\033[0m")
def test_io():
df2 = df1
with open("test.dat", "wb") as f:
pickle.dump([df1, df2], f)
with open("test.dat", "rb") as f:
vars = pickle.load(f)
df1, df2 = vars[0], vars[1]
checker = PatternSynthesizer(dispatch_gen(df1, "df1", 0, 0),
dispatch_gen(df2, "df2", 0, 1),
Info(None, None), [])
l = checker.check(df1, df2)
print("df1", "->", "df2", "\033[96m", l, "\033[0m")
def test_case2():
df2 = df1.copy()
df2.drop(['Sex', 'Name'], axis=1)
df2['Age'].fillna(0, inplace=True)
print(id(df2.index), id(df2['Age'].index))
# df2['Age'] = df2['Age'].map(lambda x: x + 1)
df2['Age'] = df2['Age'].astype(str)
df2.Survived = df2.Survived.astype(int)
checker = PatternSynthesizer(dispatch_gen(df1, "df1", 0, 0),
dispatch_gen(df2, "df2", 0, 1),
Info(None, None), [])
l = checker.check(df1, df2)
print("df1", "->", "df2", "\033[96m", checker.summary, "\033[0m")
for file in sorted(os.listdir(data_path)):
myvars = []
if file == "info.json" or file.endswith("_f.dat"):
continue
elif file.endswith(".dat"):
with open(os.path.join(data_path, file), "rb") as f:
try:
vars = pickle.load(f)
except Exception as e:
print_error("error when pickle from " + file)
print_error(e)
continue
for i in range(len(vars)):
try:
myvars.append(
dispatch_gen(vars[i][0], vars[i][1][2],
vars[i][1][0], vars[i][1][1]))
if type(vars[i][0]) == list and len(vars[i][0]) <= 3:
for j in range(len(vars[i][0])):
myvars.append(
dispatch_gen(vars[i][0][j],
vars[i][1][2] + f"[{j}]",
vars[i][1][0], vars[i][1][1]))
except:
print_error("error when dispatch var " + vars[i][1][2])
pass
# comments = static_comments[vars[0][1][0]] if vars[0][1][0] in static_comments.keys() else []
comment, json_map = handlecell(myvars, 0,
len(myvars) - 1,
Info(info, vars[0][1][0]))
# notebook.cells[code_indices[vars[0][1][0] - 1]].source = f"'''\n{comment}\n'''\n" + notebook.cells[code_indices[vars[0][1][0] - 1]].source