def classifyTestData(testFilePath,modelRoot):
"""
This method calls the traverseDecisionTreeModel() to classify the test data on the trained model and generate Confusion matrix and error at the given depth
:param testFilePath: Path to the test file
:param modelRoot: Root node of the decision tree of the trained model
"""
correctlyClassifiedInstances=0
incorrectlyClassifiedInstances=0
testDataList=[]
input=open(testFilePath,'rU')
csvObject=csv.reader(input)
label = featureList[len(featureList) -1]
classLabels = featureAndValueMapping.get(label)
classLabelCount = len(classLabels)
ConfusionMatrix = [[0 for x in range(int(classLabelCount))] for x in range(int(classLabelCount))]
for row in csvObject:
predictedLabel=traverseDecisionTreeModel(row,root)
ConfusionMatrix[int(row[len(row)- 1]) - 1][int(predictedLabel) - 1] += 1
if predictedLabel==row[len(row)-1]:
correctlyClassifiedInstances+=1
else:
incorrectlyClassifiedInstances+=1
df = DataFrame(ConfusionMatrix)
df.columns = classLabels
df.index = classLabels
print "Confusion Matrix :: \n"
print df
print "Correctly Classified Instance ",correctlyClassifiedInstances
print "Incorrectly Classified Instance ",incorrectlyClassifiedInstances
def _unstack_frame(obj, level):
from pandas.core.internals import BlockManager, make_block
if obj._is_mixed_type:
unstacker = _Unstacker(np.empty(obj.shape, dtype=bool), # dummy
obj.index, level=level,
value_columns=obj.columns)
new_columns = unstacker.get_new_columns()
new_index = unstacker.get_new_index()
new_axes = [new_columns, new_index]
new_blocks = []
mask_blocks = []
for blk in obj._data.blocks:
bunstacker = _Unstacker(blk.values.T, obj.index, level=level,
value_columns=blk.items)
new_items = bunstacker.get_new_columns()
new_values, mask = bunstacker.get_new_values()
mblk = make_block(mask.T, new_items, new_columns)
mask_blocks.append(mblk)
newb = make_block(new_values.T, new_items, new_columns)
new_blocks.append(newb)
result = DataFrame(BlockManager(new_blocks, new_axes))
mask_frame = DataFrame(BlockManager(mask_blocks, new_axes))
return result.ix[:, mask_frame.sum(0) > 0]
else:
unstacker = _Unstacker(obj.values, obj.index, level=level,
value_columns=obj.columns)
return unstacker.get_result()
def test_read_empty_dta(self):
empty_ds = DataFrame(columns=['unit'])
# GH 7369, make sure can read a 0-obs dta file
with tm.ensure_clean() as path:
empty_ds.to_stata(path,write_index=False)
empty_ds2 = read_stata(path)
tm.assert_frame_equal(empty_ds, empty_ds2)
def feature_engineering(raw_data):
input_data = raw_data[['Date','AdjClose','AdjVolume']].dropna()
train_ratio = 0.8
savedata= DataFrame(input_data)
savedata.to_csv('/home/peng/workspace/datafortrainCao.csv', header=0)
#===========================================================================
# Vol_5 = index_cal().VOL_n(input_data, 5)
# Vol_10 = index_cal().VOL_n(input_data, 10)
# Vol_15 = index_cal().VOL_n(input_data, 15)
# Vol_20 = index_cal().VOL_n(input_data, 20)
# RDV_5 = index_cal().RDV_n(input_data, 5)
# RDV_10 = index_cal().RDV_n(input_data, 10)
# RDV_15 = index_cal().RDV_n(input_data, 15)
# RDV_20 = index_cal().RDV_n(input_data, 20)
#===========================================================================
EMA15 = index_cal().EMAn(input_data, 15)
RDP_5 = index_cal().RDP_n(input_data, 5)
RDP_10 = index_cal().RDP_n(input_data, 10)
RDP_15 = index_cal().RDP_n(input_data, 15)
RDP_20 = index_cal().RDP_n(input_data, 20)
RDP_plus_5 = index_cal().RDP_plus_n(input_data, 5)
all_data = mergeColumnByDate(RDP_5,RDP_10,RDP_15,RDP_20,EMA15,RDP_plus_5)
features = all_data[['RDP-5','RDP-10','RDP-15','RDP-20','EMA15']]
features = PCA().fit_transform(features.values)
(x_train, x_test) = divideTrainTest(features, train_ratio)
objectives = all_data['RDP+5'].values
(y_train,y_real) = divideTrainTest(objectives, train_ratio)
return (x_train,y_train,x_test,y_real)
def get_daily_normals(self, start_date = None, end_date = None, stamp_year = 2001):
"""
:type start_date: datetime.datetime
:type end_date: datetime.datetime
:rtype : list , list
"""
self.stamp_day_dates = pandas.DatetimeIndex(start = datetime(stamp_year,1,1), end = date(stamp_year, 12, 31),
freq = pandas.datetools.offsets.Day())
if start_date is None:
start_date = self.time[0]
if end_date is None:
end_date = self.time[-1]
di = pandas.DatetimeIndex(data = self.time)
df = DataFrame(data = self.data, index = di, columns=["values",])
df = df.select( lambda d: start_date <= d <= end_date )
df_mean = df.groupby(by = lambda d: (d.day, d.month)).mean()
return self.stamp_day_dates, df_mean.ix[[ (d.day, d.month) for d in self.stamp_day_dates] ,"values"]
def getList(self,week, club, colList, filename):
s = pd.read_csv(filename)
df2 = DataFrame(s)
df3 = DataFrame(s)
columns = df2.columns
xlist = list()
for c in columns:
if c.upper().find("PRICE ADJUSTMENT") == -1:
if c.find(week) != -1:
xlist.append(str(c))
indexList = list()
for xcolumn in xlist:
colist = list()
colist.append(xcolumn)
df4 = DataFrame(df3, columns=colist)[~df3[xcolumn].isnull()]
for row in df4.iterrows():
if row[1][0] == club:
indexList.append(row[0])
fin = DataFrame(df2, index=indexList, columns=colList)
if fin.empty:
return
fin["Camp"] = club
fin["Week"] = week
return fin
def plot(self):
"""
Plots 2 graphs. One for N-period moving average, lower and upper bands.
One for P/N and position.
"""
columns = {"Upper Bands": self.upper_bands,
"Lower Bands": self.lower_bands,
"Moving Means": self.moving_means,
"Opening Prices": self.prices}
df = DataFrame(columns, index=self.dates)
df.plot()
fig = plt.figure(num=None, figsize=(18, 10), dpi=80, facecolor='w', edgecolor='k')
fig.add_subplot(121)
trans_dates = [tran.date for tran in self.transactions]
# we negate the value here to show profit/loss
trans = Series([-tran.value() for tran in self.transactions], index=trans_dates)
position = Series([tran.units for tran in self.transactions], index=trans_dates)
position.cumsum().plot(label="Position")
plt.xlabel("Date")
plt.ylabel("Position")
plt.title("Position over Time")
plt.legend(loc="best")
fig.add_subplot(122)
trans.cumsum().plot(label="P/L")
plt.xlabel("Date")
plt.ylabel("Profit/Loss")
plt.title("Profit and Loss over Time")
plt.legend(loc="best")
plt.show()
def pivot(self, index=None, columns=None, values=None):
"""
See DataFrame.pivot
"""
index_vals = self[index]
column_vals = self[columns]
mindex = MultiIndex.from_arrays([index_vals, column_vals])
try:
mindex._verify_integrity()
except Exception:
raise Exception("duplicate index/column pairs!")
if values is None:
items = self.columns - [index, columns]
mat = self.reindex(columns=items).values
else:
items = [values]
mat = np.atleast_2d(self[values].values).T
stacked = DataFrame(mat, index=mindex, columns=items)
if not mindex.is_lexsorted():
stacked = stacked.sortlevel(level=0)
unstacked = stacked.unstack()
if values is not None:
unstacked.columns = unstacked.columns.droplevel(0)
return unstacked
def _var_beta_panel(y, x, beta, xx, rmse, cluster_axis, nw_lags, nobs, df, nw_overlap):
from pandas.core.frame import group_agg
xx_inv = math.inv(xx)
yv = y.values
if cluster_axis is None:
if nw_lags is None:
return xx_inv * (rmse ** 2)
else:
resid = yv - np.dot(x.values, beta)
m = (x.values.T * resid).T
xeps = math.newey_west(m, nw_lags, nobs, df, nw_overlap)
return np.dot(xx_inv, np.dot(xeps, xx_inv))
else:
Xb = np.dot(x.values, beta).reshape((len(x.values), 1))
resid = DataFrame(yv[:, None] - Xb, index=y.index, columns=["resid"])
if cluster_axis == 1:
x = x.swaplevel(0, 1).sortlevel(0)
resid = resid.swaplevel(0, 1).sortlevel(0)
m = group_agg(x.values * resid.values, x.index._bounds, lambda x: np.sum(x, axis=0))
if nw_lags is None:
nw_lags = 0
xox = 0
for i in range(len(x.index.levels[0])):
xox += math.newey_west(m[i : i + 1], nw_lags, nobs, df, nw_overlap)
return np.dot(xx_inv, np.dot(xox, xx_inv))
def test_missing_value_generator(self):
types = ('b','h','l')
df = DataFrame([[0.0]],columns=['float_'])
with tm.ensure_clean() as path:
df.to_stata(path)
with StataReader(path) as rdr:
valid_range = rdr.VALID_RANGE
expected_values = ['.' + chr(97 + i) for i in range(26)]
expected_values.insert(0, '.')
for t in types:
offset = valid_range[t][1]
for i in range(0,27):
val = StataMissingValue(offset+1+i)
self.assertTrue(val.string == expected_values[i])
# Test extremes for floats
val = StataMissingValue(struct.unpack('<f',b'\x00\x00\x00\x7f')[0])
self.assertTrue(val.string == '.')
val = StataMissingValue(struct.unpack('<f',b'\x00\xd0\x00\x7f')[0])
self.assertTrue(val.string == '.z')
# Test extremes for floats
val = StataMissingValue(struct.unpack('<d',b'\x00\x00\x00\x00\x00\x00\xe0\x7f')[0])
self.assertTrue(val.string == '.')
val = StataMissingValue(struct.unpack('<d',b'\x00\x00\x00\x00\x00\x1a\xe0\x7f')[0])
self.assertTrue(val.string == '.z')
def export_converted_values(self):
"""
This function is called initially to convert per-100g values to per serving values
Once this function is invoked, new file is generated which serves as Database
This function will need to be called only one time
:return:
"""
file_converted = self.file_converted_values
data_file = self.file_database
data = self.read_csv(data_file)
converted_data = list()
for item in data.values:
converted_list = list(item[0:2])
sub_item = item[2:50]
for nutrient in sub_item:
import math
if math.isnan(nutrient):
nutrient = 0
converted_list.append(nutrient * sub_item[47] / 100)
converted_list.append(item[50])
converted_data.append(converted_list)
if len(self.cols) == 0:
for col_name in list(data._info_axis._data):
self.cols.append(col_name)
df = DataFrame(data=converted_data, columns=self.cols)
df.to_csv(file_converted, index=False)
print 'File has been exported'
def get_result(self):
if self._is_series:
if self.axis == 0:
new_data = com._concat_compat([x.get_values() for x in self.objs])
name = com._consensus_name_attr(self.objs)
return Series(new_data, index=self.new_axes[0], name=name).__finalize__(self, method='concat')
else:
data = dict(zip(range(len(self.objs)), self.objs))
index, columns = self.new_axes
tmpdf = DataFrame(data, index=index)
if columns is not None:
tmpdf.columns = columns
return tmpdf.__finalize__(self, method='concat')
else:
mgrs_indexers = []
for obj in self.objs:
mgr = obj._data
indexers = {}
for ax, new_labels in enumerate(self.new_axes):
if ax == self.axis:
# Suppress reindexing on concat axis
continue
obj_labels = mgr.axes[ax]
if not new_labels.equals(obj_labels):
indexers[ax] = obj_labels.reindex(new_labels)[1]
mgrs_indexers.append((obj._data, indexers))
new_data = concatenate_block_managers(
mgrs_indexers, self.new_axes, concat_axis=self.axis, copy=self.copy)
if not self.copy:
new_data._consolidate_inplace()
return self.objs[0]._from_axes(new_data, self.new_axes).__finalize__(self, method='concat')
def test_read_write_dta12(self):
original = DataFrame(
[(1, 2, 3, 4, 5, 6)],
columns=[
"astringwithmorethan32characters_1",
"astringwithmorethan32characters_2",
"+",
"-",
"short",
"delete",
],
)
formatted = DataFrame(
[(1, 2, 3, 4, 5, 6)],
columns=[
"astringwithmorethan32characters_",
"_0astringwithmorethan32character",
"_",
"_1_",
"_short",
"_delete",
],
)
formatted.index.name = "index"
formatted = formatted.astype(np.int32)
with tm.ensure_clean() as path:
with warnings.catch_warnings(record=True) as w:
original.to_stata(path, None)
tm.assert_equal(len(w), 1) # should get a warning for that format.
written_and_read_again = self.read_dta(path)
tm.assert_frame_equal(written_and_read_again.set_index("index"), formatted)
def _wrap_aggregated_output(self, output, mask, comp_ids):
agg_axis = 0 if self.axis == 1 else 1
agg_labels = self._obj_with_exclusions._get_axis(agg_axis)
if len(output) == len(agg_labels):
output_keys = agg_labels
else:
output_keys = sorted(output)
try:
output_keys.sort()
except Exception: # pragma: no cover
pass
if isinstance(agg_labels, MultiIndex):
output_keys = MultiIndex.from_tuples(output_keys,
names=agg_labels.names)
if not self.as_index:
result = DataFrame(output, columns=output_keys)
group_levels = self._get_group_levels(mask, comp_ids)
for i, (name, labels) in enumerate(group_levels):
result.insert(i, name, labels)
result = result.consolidate()
else:
index = self._get_multi_index(mask, comp_ids)
result = DataFrame(output, index=index, columns=output_keys)
if self.axis == 1:
result = result.T
return result
def test_missing_value_generator(self):
types = ("b", "h", "l")
df = DataFrame([[0.0]], columns=["float_"])
with tm.ensure_clean() as path:
df.to_stata(path)
with StataReader(path) as rdr:
valid_range = rdr.VALID_RANGE
expected_values = ["." + chr(97 + i) for i in range(26)]
expected_values.insert(0, ".")
for t in types:
offset = valid_range[t][1]
for i in range(0, 27):
val = StataMissingValue(offset + 1 + i)
self.assertTrue(val.string == expected_values[i])
# Test extremes for floats
val = StataMissingValue(struct.unpack("<f", b"\x00\x00\x00\x7f")[0])
self.assertTrue(val.string == ".")
val = StataMissingValue(struct.unpack("<f", b"\x00\xd0\x00\x7f")[0])
self.assertTrue(val.string == ".z")
# Test extremes for floats
val = StataMissingValue(struct.unpack("<d", b"\x00\x00\x00\x00\x00\x00\xe0\x7f")[0])
self.assertTrue(val.string == ".")
val = StataMissingValue(struct.unpack("<d", b"\x00\x00\x00\x00\x00\x1a\xe0\x7f")[0])
self.assertTrue(val.string == ".z")
def stack_sparse_frame(frame):
"""
Only makes sense when fill_value is NaN
"""
lengths = [s.sp_index.npoints for _, s in compat.iteritems(frame)]
nobs = sum(lengths)
# this is pretty fast
minor_labels = np.repeat(np.arange(len(frame.columns)), lengths)
inds_to_concat = []
vals_to_concat = []
# TODO: Figure out whether this can be reached.
# I think this currently can't be reached because you can't build a SparseDataFrame
# with a non-np.NaN fill value (fails earlier).
for _, series in compat.iteritems(frame):
if not np.isnan(series.fill_value):
raise TypeError('This routine assumes NaN fill value')
int_index = series.sp_index.to_int_index()
inds_to_concat.append(int_index.indices)
vals_to_concat.append(series.sp_values)
major_labels = np.concatenate(inds_to_concat)
stacked_values = np.concatenate(vals_to_concat)
index = MultiIndex(levels=[frame.index, frame.columns],
labels=[major_labels, minor_labels],
verify_integrity=False)
lp = DataFrame(stacked_values.reshape((nobs, 1)), index=index,
columns=['foo'])
return lp.sortlevel(level=0)
def stack_sparse_frame(frame):
"""
Only makes sense when fill_value is NaN
"""
lengths = [s.sp_index.npoints for _, s in frame.iteritems()]
nobs = sum(lengths)
# this is pretty fast
minor_labels = np.repeat(np.arange(len(frame.columns)), lengths)
inds_to_concat = []
vals_to_concat = []
for _, series in frame.iteritems():
if not np.isnan(series.fill_value):
raise Exception('This routine assumes NaN fill value')
int_index = series.sp_index.to_int_index()
inds_to_concat.append(int_index.indices)
vals_to_concat.append(series.sp_values)
major_labels = np.concatenate(inds_to_concat)
stacked_values = np.concatenate(vals_to_concat)
index = MultiIndex(levels=[frame.index, frame.columns],
labels=[major_labels, minor_labels])
lp = DataFrame(stacked_values.reshape((nobs, 1)), index=index,
columns=['foo'])
return lp.sortlevel(level=0)
def test_read_write_dta12(self):
original = DataFrame([(1, 2, 3, 4, 5, 6)],
columns=['astringwithmorethan32characters_1',
'astringwithmorethan32characters_2',
'+',
'-',
'short',
'delete'])
formatted = DataFrame([(1, 2, 3, 4, 5, 6)],
columns=['astringwithmorethan32characters_',
'_0astringwithmorethan32character',
'_',
'_1_',
'_short',
'_delete'])
formatted.index.name = 'index'
formatted = formatted.astype(np.int32)
with tm.ensure_clean() as path:
with warnings.catch_warnings(record=True) as w:
original.to_stata(path, None)
tm.assert_equal(len(w), 1) # should get a warning for that format.
written_and_read_again = self.read_dta(path)
tm.assert_frame_equal(written_and_read_again.set_index('index'), formatted)
def pivot(self, index=None, columns=None, values=None):
"""
See DataFrame.pivot
"""
index_vals = self[index]
column_vals = self[columns]
mindex = MultiIndex.from_arrays([index_vals, column_vals],
names=[index, columns])
if values is None:
items = self.columns - [index, columns]
mat = self.reindex(columns=items).values
else:
items = [values]
mat = np.atleast_2d(self[values].values).T
stacked = DataFrame(mat, index=mindex, columns=items)
if not mindex.is_lexsorted():
stacked = stacked.sortlevel(level=0)
unstacked = stacked.unstack()
if values is not None:
unstacked.columns = unstacked.columns.droplevel(0)
return unstacked
def _wrap_applied_output(self, keys, values, not_indexed_same=False):
if len(keys) == 0:
return Series([])
key_names = [ping.name for ping in self.groupings]
if isinstance(values[0], Series):
if not_indexed_same:
data_dict = dict(zip(keys, values))
result = DataFrame(data_dict).T
if len(self.groupings) > 1:
result.index = MultiIndex.from_tuples(keys, names=key_names)
return result
else:
cat_values = np.concatenate([x.values for x in values])
cat_index = values[0].index
if len(values) > 1:
cat_index = cat_index.append([x.index for x in values[1:]])
return Series(cat_values, index=cat_index)
elif isinstance(values[0], DataFrame):
# possible that Series -> DataFrame by applied function
return self._wrap_frames(keys, values,
not_indexed_same=not_indexed_same)
else:
if len(self.groupings) > 1:
index = MultiIndex.from_tuples(keys, names=key_names)
return Series(values, index)
else:
return Series(values, keys)
def testEnsembleForecastWeightCombinesForecasts(self):
result = self.weight(self.forecasts)
self.assertIsInstance(result, Forecast)
for i in [0, 1, 5, 10, 19]:
expected = [fcst.mean.iloc[i] for fcst in self.forecasts]
expected = DataFrame(expected)
self.assertTrue(result.mean.iloc[i].equals(expected.mean()))
def getCamps(self,week):
s = pd.read_csv("D:/UTDallasStudy/summer.csv")
df2 = DataFrame(s)
df3 = DataFrame(s)
columns = df2.columns
x = set()
xlist = list()
ylist = list()
for c in columns:
if c.upper().find("PRICE ADJUSTMENT") == -1:
if c.find(week) != -1:
x.add(re.split("\.?", str(c))[0])
ylist.append(c)
else:
x.add(str(c))
for x1 in x: xlist.append(x1)
xlist.sort(cmp=None, key=None, reverse=False)
campset = set()
for y in ylist:
clist = list()
clist.append(y)
res = DataFrame(df3, columns=clist)[~df3[y].isnull()]
for row in res.iterrows():
campName = row[1][0]
campset.add(campName)
camplist = list()
for camp in campset: camplist.append(camp)
camplist.sort(cmp=None, key=None, reverse=False)
return camplist
def generate_input_df(self, n_topics, vocab_size, document_length, n_docs,
previous_vocab=None, vocab_prefix=None,
df_outfile=None, vocab_outfile=None,
n_bags=1):
print "Generating input DF"
# word_dists is the topic x document_length matrix
word_dists = self.generate_word_dists(n_topics, vocab_size, document_length)
# generate each document x terms vector
docs = np.zeros((vocab_size, n_docs), dtype=int64)
for i in range(n_docs):
docs[:, i] = self.generate_document(word_dists, n_topics, vocab_size, document_length)
if previous_vocab is not None:
width = vocab_size/n_topics
high = int(document_length / width)
# randomly initialises the previous_vocab part
additional = np.random.randint(high, size=(len(previous_vocab), n_docs))
docs = np.vstack((additional, docs))
df = DataFrame(docs)
df = df.transpose()
print df.shape
if self.make_plot:
self._plot_nicely(df, 'Documents X Terms', 'Terms', 'Docs')
if df_outfile is not None:
df.to_csv(df_outfile)
print "Generating vocabularies"
# initialises vocab to either previous vocab or a blank list
if previous_vocab is not None:
vocab = previous_vocab.tolist()
else:
vocab = []
# add new words
for n in range(vocab_size):
if vocab_prefix is None:
word = "word_" + str(n)
else:
word = vocab_prefix + "_word_" + str(n)
# if more than one bag, then initialise word type too
if n_bags > 1:
word_type = np.random.randint(n_bags)
tup = (word, word_type)
vocab.append(tup)
else:
vocab.append(word)
# save to txt
vocab = np.array(vocab)
if vocab_outfile is not None:
np.savetxt(vocab_outfile, vocab, fmt='%s')
return df, vocab
def get_result(self):
# series only
if self._is_series:
# stack blocks
if self.axis == 0:
new_data = com._concat_compat([x._values for x in self.objs])
name = com._consensus_name_attr(self.objs)
return (Series(new_data, index=self.new_axes[0],
name=name,
dtype=new_data.dtype)
.__finalize__(self, method='concat'))
# combine as columns in a frame
else:
data = dict(zip(range(len(self.objs)), self.objs))
index, columns = self.new_axes
tmpdf = DataFrame(data, index=index)
# checks if the column variable already stores valid column
# names (because set via the 'key' argument in the 'concat'
# function call. If that's not the case, use the series names
# as column names
if (columns.equals(Index(np.arange(len(self.objs)))) and
not self.ignore_index):
columns = np.array([data[i].name
for i in range(len(data))],
dtype='object')
indexer = isnull(columns)
if indexer.any():
columns[indexer] = np.arange(len(indexer[indexer]))
tmpdf.columns = columns
return tmpdf.__finalize__(self, method='concat')
# combine block managers
else:
mgrs_indexers = []
for obj in self.objs:
mgr = obj._data
indexers = {}
for ax, new_labels in enumerate(self.new_axes):
if ax == self.axis:
# Suppress reindexing on concat axis
continue
obj_labels = mgr.axes[ax]
if not new_labels.equals(obj_labels):
indexers[ax] = obj_labels.reindex(new_labels)[1]
mgrs_indexers.append((obj._data, indexers))
new_data = concatenate_block_managers(
mgrs_indexers, self.new_axes,
concat_axis=self.axis, copy=self.copy)
if not self.copy:
new_data._consolidate_inplace()
return (self.objs[0]._from_axes(new_data, self.new_axes)
.__finalize__(self, method='concat'))
def test_write_missing_strings(self):
original = DataFrame([["1"], [None]], columns=["foo"])
expected = DataFrame([["1"], [""]], columns=["foo"])
expected.index.name = "index"
with tm.ensure_clean() as path:
original.to_stata(path)
written_and_read_again = self.read_dta(path)
tm.assert_frame_equal(written_and_read_again.set_index("index"), expected)
def test_no_index(self):
columns = ["x", "y"]
original = DataFrame(np.reshape(np.arange(10.0), (5, 2)), columns=columns)
original.index.name = "index_not_written"
with tm.ensure_clean() as path:
original.to_stata(path, write_index=False)
written_and_read_again = self.read_dta(path)
tm.assertRaises(KeyError, lambda: written_and_read_again["index_not_written"])
class XLSDataFrameWriter(object):
def __init__(self, records, columns):
self.dataframe = DataFrame(records, columns=columns)
def write_to_excel(self, excel_writer, sheet_name, header=False,
index=False):
self.dataframe.to_excel(excel_writer, sheet_name, header=header,
index=index)
def test_column_order_plus_index(self):
query = "SELECT 'a' as STRING_1, 'b' as STRING_2, 'c' as STRING_3"
col_order = ['STRING_3', 'STRING_2']
result_frame = gbq.read_gbq(query, project_id=PROJECT_ID, index_col='STRING_1', col_order=col_order)
correct_frame = DataFrame({'STRING_1' : ['a'], 'STRING_2' : ['b'], 'STRING_3' : ['c']})
correct_frame.set_index('STRING_1', inplace=True)
correct_frame = correct_frame[col_order]
tm.assert_frame_equal(result_frame, correct_frame)
def test_column_order_plus_index(self):
query = "SELECT 'a' as STRING_1, 'b' as STRING_2, 'c' as STRING_3"
col_order = ["STRING_3", "STRING_2"]
result_frame = gbq.read_gbq(query, project_id=PROJECT_ID, index_col="STRING_1", col_order=col_order)
correct_frame = DataFrame({"STRING_1": ["a"], "STRING_2": ["b"], "STRING_3": ["c"]})
correct_frame.set_index("STRING_1", inplace=True)
correct_frame = correct_frame[col_order]
tm.assert_frame_equal(result_frame, correct_frame)
def test_excessively_long_string(self):
str_lens = (1, 244, 500)
s = {}
for str_len in str_lens:
s['s' + str(str_len)] = Series(['a' * str_len, 'b' * str_len, 'c' * str_len])
original = DataFrame(s)
with tm.assertRaises(ValueError):
with tm.ensure_clean() as path:
original.to_stata(path)
def rpy2py_dataframe(obj):
items = OrderedDict((k, rpy2py(v) if isinstance(v, Sexp) else v)
for k, v in obj.items())
res = PandasDataFrame.from_dict(items)
res.index = obj.rownames
return res
def makeNewsDataCsv(cls,
cur=None,
start_date=None,
end_date=None,
basic_path=None,
word_trend_file=None,
news_file=None,
output_file=None,
stock_id=None):
if cur == None or start_date == None or end_date == None or word_trend_file is None or output_file == None or stock_id == None:
return None
if basic_path is None:
basic_path = os.path.dirname(os.path.abspath(__file__))
news_path = os.path.join(basic_path, news_file)
word_trend_path = os.path.join(basic_path, word_trend_file)
output_path = os.path.join(basic_path, output_file)
VTool.makeDirs(files=[output_path])
columns = [
"stock_id", "date", "opening", "closing", "difference",
"percentage_difference", "lowest", "highest", "volume", "amount",
"rate"
] + ["news_pos_num", "news_neg_num"]
data = {}
for k in columns:
data[k] = []
pd.DataFrame(data).to_csv(output_path, index=False, columns=columns)
word_trend = {}
word_trend_temp = pd.read_csv(word_trend_path)
for k in word_trend_temp["0"].keys():
word_trend[word_trend_temp["0"][k]] = [
word_trend_temp["1"][k], word_trend_temp["2"][k]
]
p_up = word_trend['total_words'][0] / (word_trend['total_words'][0] +
word_trend['total_words'][1])
p_down = word_trend['total_words'][1] / (word_trend['total_words'][0] +
word_trend['total_words'][1])
cur.execute(
"SELECT count(*) as count FROM history WHERE stock_id = '%s' and date between '%s' and '%s' "
% (stock_id, start_date, end_date))
count = cur.fetchall()
count = count[0][0]
skip = 100
slimit = 0
while slimit < count:
cur.execute(
"SELECT stock_id, opening, closing, difference, percentage_difference, lowest, highest, volume, amount, date FROM history WHERE stock_id = '%s' and date between '%s' and '%s' order by date asc, stock_id asc limit %d,%d "
% (stock_id, start_date, end_date, 0 if slimit - 1 < 0 else
slimit - 1, skip if slimit - 1 < 0 else skip + 1))
slimit += skip
history_tt = cur.fetchall()
history_t = []
for h in history_tt:
history_t.append([
int(h[0]),
float(h[1]),
float(h[2]),
float(h[3]),
float(h[4]),
float(h[5]),
float(h[6]),
float(h[7]),
float(h[8]),
str(h[9])
])
del history_tt
history_temp = []
for h in zip(*history_t):
history_temp.append(h)
history = {
'stock_id': history_temp[0],
'opening': history_temp[1],
'closing': history_temp[2],
'difference': history_temp[3],
'percentage_difference': history_temp[4],
'lowest': history_temp[5],
'highest': history_temp[6],
'volume': history_temp[7],
'amount': history_temp[8],
'date': history_temp[9]
}
del history_t, history_temp
history = DataFrame(history)
g_history = history.groupby(by=['stock_id'])
#0.01 -> 1 % 保留2位小数
history['rate'] = 100 * (g_history.shift(0)["closing"] /
g_history.shift(1)["closing"] - 1)
history.dropna(axis=0,
how='any',
thresh=None,
subset=None,
inplace=True)
'''
'''
sdate = str(history['date'][history['date'].keys()[0]])
edate = str(history['date'][history['date'].keys()[-1]])
# sdate = datetime.datetime.strptime(sdate,'%Y-%m-%d')
# sdate = (sdate - datetime.timedelta(days=0)).strftime('%Y-%m-%d')
cur.execute(
"SELECT GROUP_CONCAT(id SEPARATOR ','), time FROM news WHERE time between '%s' and '%s' group by time"
% (sdate, edate))
news_temp = cur.fetchall()
news_by_date = {}
news_by_id = {}
for n in news_temp:
news_by_date[str(n[1])] = n[0].split(",")
for nid in news_by_date[str(n[1])]:
news_by_id[nid] = None
del news_temp
nid_len = len(news_by_id)
reader = pd.read_csv(news_path, chunksize=1000)
for sentences in reader:
if nid_len > 0:
for k in sentences['1'].keys():
nid = str(sentences['0'][k])
if nid in news_by_id and news_by_id[nid] == None:
news_by_id[nid] = str(sentences['1'][k]).split(" ")
wp_up = p_up
wp_down = p_down
for w in news_by_id[nid]:
if w not in word_trend:
wp_up *= (1 / word_trend['total_words'][0])
wp_down *= (1 /
word_trend['total_words'][1])
else:
if word_trend[w][0] > 0:
wp_up *= word_trend[w][0]
else:
wp_up *= (1 /
word_trend['total_words'][0])
if word_trend[w][1] > 0:
wp_down *= word_trend[w][1]
else:
wp_down *= (
1 / word_trend['total_words'][1])
while True:
if wp_up < 1 and wp_down < 1:
wp_up *= 10
wp_down *= 10
else:
break
news_by_id[nid] = [
wp_up / (wp_up + wp_down),
-1 * wp_down / (wp_up + wp_down)
]
nid_len -= 1
if nid_len <= 0:
break
else:
break
reader.close()
del reader, sentences
for d in news_by_date:
sumn = [0, 0]
for nid in news_by_date[d]:
sumn[0] += news_by_id[nid][0]
sumn[1] += news_by_id[nid][1]
le = len(news_by_date[d])
if le > 0:
sumn[0] /= le
sumn[1] /= le
news_by_date[d] = sumn
print(d)
history['news_pos_num'] = 0
history['news_neg_num'] = 0
for i in history.index:
history.loc[i, 'rate'] = str(
np.round(float(history['rate'][i]), 2))
if str(history['date'][i]) in news_by_date:
history.loc[i, 'news_pos_num'] = str(
np.round(
float(news_by_date[str(history['date'][i])][0]),
2))
history.loc[i, 'news_neg_num'] = str(
np.round(
float(news_by_date[str(history['date'][i])][1]),
2))
else:
history.loc[i, 'news_pos_num'] = "0"
history.loc[i, 'news_neg_num'] = "0"
#将经过标准化的数据处理成训练集和测试集可接受的形式
def func_train_data(data_stock):
if cls.groupby_skip == False:
cls.groupby_skip = True
return None
print("正在处理的股票代码:%06s" % data_stock.name)
data = {}
for k in columns:
data[k] = []
for i in range(len(data_stock) - 1):
for k in data:
data[k].append(data_stock.iloc[i][k])
pd.DataFrame(data).to_csv(output_path,
index=False,
header=False,
mode="a",
columns=columns)
g_stock = history.groupby(by=["stock_id"])
#清空接收路径下的文件，初始化列名
cls.groupby_skip = False
g_stock.apply(func_train_data)
if lista_nombres[i][-2] == lista_nombres[i][1]:
n2 = ""
medico = clases.Medico(n1, n2, ap1, ap2, lista_ruts[i], lista_edad[i],
lista_emails[i], lista_numero[i],
lista_especialidad[i])
lista_medicos.append(medico)
clinica_objeto = clases.Clinica("Clinica de la Salud", "Público",
"Avenida Verdadera #123, Rancagua", "",
lista_medicos, lista_pacientes)
lista_citas = []
cita_vacia = clases.Cita("", "", "", "")
cita_csv = pd.read_csv('./datos/Citas.csv')
cita_csv = DataFrame(cita_csv)
codigo = cita_csv["codigo"].values
rut_paciente = cita_csv["rut paciente"].values
rut_medico = cita_csv["rut medico"].values
fecha_citada = cita_csv["fecha citada"].values
fecha_creacion = cita_csv["fecha de creacion"].values
modalidad = cita_csv["modalidad"].values
prestacion = cita_csv["prestacion"].values
confirmada = cita_csv["confirmada"].values
tiempo_restante = cita_csv["tiempo restante"].values
for i in range(len(codigo)):
cita_vacia.setCodigo(codigo[i])
cita_vacia.setPaciente(clinica_objeto.buscarPaciente(rut_paciente[i])[0])
cita_vacia.setMedico(clinica_objeto.buscarMedico(rut_medico[i])[0])
cita_vacia.setFechaCitada(parser.parse(fecha_citada[i]))
model.fit(x=X_train,
y=y_train,
epochs=3,
batch_size=128,
verbose=2,
validation_split=0.1)
#预测
y_predict = model.predict(X_test)
#转换预测结果
y_predict_label = label2tag(predictions=y_predict, y=y)
#统计正确率
Y_test = label2tag(predictions=y_test, y=y)
print(
sum([y_predict_label[i] == Y_test[i]
for i in range(len(y_predict))]) / len(y_predict))
#导入另一个测试集进行预测，并导出结果
filename = 'xiaomi5a.csv'
test_data = pd.read_csv(filename)
x = test_data['comment']
X_cut = cut_texts(texts=x, need_cut=True, word_len=2, savepath=None)
X_seq = text2seq(texts_cut=X_cut, maxlen=maxlen, tokenizer=tokenizer)
X_seq = np.array(X_seq)
y_predict = model.predict(X_seq)
y_predict_label = label2tag(predictions=y_predict, y=y)
#Series转成dateframe
out_x = x.to_frame(name=None)
out_y = DataFrame(y_predict_label)
out_x.to_csv('x.csv')
out_y.to_csv('y.csv')
#model
starttime = datetime.datetime.now() #Caculate time
sample_model = KMeans(n_clusters=10).fit(images_train_sample) #K-Means
endtime = datetime.datetime.now() #Caculate time
scikit_learn_execution_time = (endtime - starttime).seconds
print('scikit-learn execution time:',
scikit_learn_execution_time) #Caculate time 429s
#objective function value
cluster = sample_model.labels_
objective_function_value = sample_model.inertia_ #394810072745.4526
print('scikit-learn objective function value:', objective_function_value)
#accuracy
crosstable_data = {'label': labels_train_sample, 'cluster': list(cluster)}
df = DataFrame(crosstable_data)
crosstable = pd.crosstab(index=df['label'], columns=df['cluster'])
scikit_accuracy = sum(crosstable.max(axis=0)) / sum(crosstable.sum()) #0.22124
print('scikit-learn accuracy:', scikit_accuracy)
#PART3 my kmeans
######
#####
####
###
##
#
#model
starttime_2 = datetime.datetime.now() #Caculate start time
cluster_center, cluster_assign = Kmeans(array(images_train_sample), 10)
def test_stata_doc_examples(self):
with tm.ensure_clean() as path:
df = DataFrame(np.random.randn(10, 2), columns=list('AB'))
df.to_stata(path)
target = cl.astype('int')
print (target)
# 切分訓練與測試資料
train_X, test_X, train_y, test_y = train_test_split(data, target, train_size = 0.9, random_state = 42)
print (train_y)
# 建立分類器
clf = neighbors.KNeighborsClassifier(n_neighbors = 25)
data_clf = clf.fit(train_X, train_y)
# 預測
test_y_predicted = data_clf.predict(test_X)
"""print (test_y_predicted)
# 標準答案
print (test_y)"""
# 績效
accuracy = metrics.accuracy_score(test_y, test_y_predicted)
print "accuracy : ", accuracy
precision = metrics.precision_score(test_y, test_y_predicted, average='macro')
print "precision : ", precision
recall = metrics.recall_score(test_y, test_y_predicted, average='macro')
print "recall : ", recall
f_measure = 2 * (precision * recall / (precision + recall))
print "f_measure : ", f_measure
output = {'click' : test_y_predicted}
output = DataFrame(output)
output.to_csv('output.csv', sep=',', index = 0)
def predict_role(ps):
fd = pd.read_csv('player_label.csv')
df_obj = fd.label
fd.label = df_obj.apply(lambda x: str(x).strip())
print(fd.label)
test_set = fd[['label']]
train_set = fd[[
'attacking_work_rate', 'defensive_work_rate', 'crossing', 'finishing',
'heading_accuracy', 'short_passing', 'volleys', 'dribbling', 'curve',
'free_kick_accuracy', 'long_passing', 'ball_control', 'acceleration',
'sprint_speed', 'agility', 'reactions', 'balance', 'shot_power',
'jumping', 'stamina', 'strength', 'long_shots', 'aggression',
'interceptions', 'positioning', 'vision', 'penalties', 'marking',
'standing_tackle', 'sliding_tackle', 'gk_diving', 'gk_handling',
'gk_kicking', 'gk_positioning', 'gk_reflexes'
]]
train_set = train_set[1:]
test_set = test_set[1:]
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(train_set,
test_set,
test_size=0.33,
random_state=12)
from sklearn.naive_bayes import MultinomialNB
clf_NB = MultinomialNB().fit(x_train, y_train)
predicted = clf_NB.predict(x_test)
import numpy as np
from sklearn import metrics
print("#################### NB ######################")
confusion_matrix_NB = metrics.confusion_matrix(y_test, predicted)
print(confusion_matrix_NB)
accuracy_NB = metrics.accuracy_score(y_test, predicted)
print(accuracy_NB)
# print(metrics.classification_report(y_test, predicted))
print("##############################################")
from sklearn import tree
clf_tree = tree.DecisionTreeClassifier().fit(x_train, y_train)
predicted = clf_tree.predict(x_test)
print("#################### Decision Tree ######################")
print(metrics.confusion_matrix(y_test, predicted))
accuracy_DT = metrics.accuracy_score(y_test, predicted)
print(accuracy_DT)
# print(metrics.classification_report(y_test, predicted))
print("##############################################")
from sklearn.linear_model import SGDClassifier
clf_SGD = SGDClassifier().fit(x_train, y_train)
predicted = clf_SGD.predict(x_test)
print("#################### SGD Classifier ######################")
print(metrics.confusion_matrix(y_test, predicted))
accuracy_SGD = metrics.accuracy_score(y_test, predicted)
print(accuracy_SGD)
print("##############################################")
from pandas.core.frame import DataFrame
predict_data = DataFrame(ps)
print(
"----------------------&&&&&&&&&&&&&&&&&&&&&&&&&&&&&-----------------------"
)
print(predict_data)
print(
"----------------------&&&&&&&&&&&&&&&&&&&&&&&&&&&&&-----------------------"
)
predict_data = predict_data.iloc[:, 7:]
print(
"---------------------- become 38 ----------------------------------------"
)
print(predict_data)
print(
"---------------------- become 38 ----------------------------------------"
)
accuracy_list = [accuracy_NB, accuracy_DT, accuracy_SGD]
if max(accuracy_list) == accuracy_NB:
clf_model = clf_NB
elif max(accuracy_list) == accuracy_DT:
clf_model = clf_tree
elif max(accuracy_list) == accuracy_SGD:
clf_model = clf_SGD
predicted = clf_model.predict(predict_data)
print("************* model selection ****************")
print(clf_model)
pd.value_counts(predicted)
print(predicted)
print(type(predicted))
return predicted.tolist()
def __init__(self,
data=None,
index=None,
columns=None,
default_kind=None,
default_fill_value=None,
dtype=None,
copy=False):
# pick up the defaults from the Sparse structures
if isinstance(data, SparseDataFrame):
if index is None:
index = data.index
if columns is None:
columns = data.columns
if default_fill_value is None:
default_fill_value = data.default_fill_value
if default_kind is None:
default_kind = data.default_kind
elif isinstance(data, (SparseSeries, SparseArray)):
if index is None:
index = data.index
if default_fill_value is None:
default_fill_value = data.fill_value
if columns is None and hasattr(data, 'name'):
columns = [data.name]
if columns is None:
raise Exception("cannot pass a series w/o a name or columns")
data = {columns[0]: data}
if default_fill_value is None:
default_fill_value = np.nan
if default_kind is None:
default_kind = 'block'
self._default_kind = default_kind
self._default_fill_value = default_fill_value
if is_scipy_sparse(data):
mgr = self._init_spmatrix(data,
index,
columns,
dtype=dtype,
fill_value=default_fill_value)
elif isinstance(data, dict):
mgr = self._init_dict(data, index, columns, dtype=dtype)
elif isinstance(data, (np.ndarray, list)):
mgr = self._init_matrix(data, index, columns, dtype=dtype)
elif isinstance(data, SparseDataFrame):
mgr = self._init_mgr(data._data,
dict(index=index, columns=columns),
dtype=dtype,
copy=copy)
elif isinstance(data, DataFrame):
mgr = self._init_dict(data, data.index, data.columns, dtype=dtype)
elif isinstance(data, Series):
mgr = self._init_dict(data.to_frame(),
data.index,
columns=None,
dtype=dtype)
elif isinstance(data, BlockManager):
mgr = self._init_mgr(data,
axes=dict(index=index, columns=columns),
dtype=dtype,
copy=copy)
elif data is None:
data = DataFrame()
if index is None:
index = Index([])
else:
index = ensure_index(index)
if columns is None:
columns = Index([])
else:
for c in columns:
data[c] = SparseArray(np.nan,
index=index,
kind=self._default_kind,
fill_value=self._default_fill_value)
mgr = to_manager(data, columns, index)
if dtype is not None:
mgr = mgr.astype(dtype)
else:
msg = ('SparseDataFrame called with unknown type "{data_type}" '
'for data argument')
raise TypeError(msg.format(data_type=type(data).__name__))
generic.NDFrame.__init__(self, mgr)
def _get_dummies_1d(data,
prefix,
prefix_sep='_',
dummy_na=False,
sparse=False,
drop_first=False,
dtype=None):
# Series avoids inconsistent NaN handling
codes, levels = _factorize_from_iterable(Series(data))
if dtype is None:
dtype = np.uint8
dtype = np.dtype(dtype)
if is_object_dtype(dtype):
raise ValueError("dtype=object is not a valid dtype for get_dummies")
def get_empty_Frame(data, sparse):
if isinstance(data, Series):
index = data.index
else:
index = np.arange(len(data))
if not sparse:
return DataFrame(index=index)
else:
return SparseDataFrame(index=index, default_fill_value=0)
# if all NaN
if not dummy_na and len(levels) == 0:
return get_empty_Frame(data, sparse)
codes = codes.copy()
if dummy_na:
codes[codes == -1] = len(levels)
levels = np.append(levels, np.nan)
# if dummy_na, we just fake a nan level. drop_first will drop it again
if drop_first and len(levels) == 1:
return get_empty_Frame(data, sparse)
number_of_cols = len(levels)
if prefix is not None:
dummy_strs = [
u'{prefix}{sep}{level}'
if isinstance(v, text_type) else '{prefix}{sep}{level}'
for v in levels
]
dummy_cols = [
dummy_str.format(prefix=prefix, sep=prefix_sep, level=v)
for dummy_str, v in zip(dummy_strs, levels)
]
else:
dummy_cols = levels
if isinstance(data, Series):
index = data.index
else:
index = None
if sparse:
sparse_series = {}
N = len(data)
sp_indices = [[] for _ in range(len(dummy_cols))]
for ndx, code in enumerate(codes):
if code == -1:
# Blank entries if not dummy_na and code == -1, #GH4446
continue
sp_indices[code].append(ndx)
if drop_first:
# remove first categorical level to avoid perfect collinearity
# GH12042
sp_indices = sp_indices[1:]
dummy_cols = dummy_cols[1:]
for col, ixs in zip(dummy_cols, sp_indices):
sarr = SparseArray(np.ones(len(ixs), dtype=dtype),
sparse_index=IntIndex(N, ixs),
fill_value=0,
dtype=dtype)
sparse_series[col] = SparseSeries(data=sarr, index=index)
out = SparseDataFrame(sparse_series,
index=index,
columns=dummy_cols,
default_fill_value=0,
dtype=dtype)
return out
else:
dummy_mat = np.eye(number_of_cols, dtype=dtype).take(codes, axis=0)
if not dummy_na:
# reset NaN GH4446
dummy_mat[codes == -1] = 0
if drop_first:
# remove first GH12042
dummy_mat = dummy_mat[:, 1:]
dummy_cols = dummy_cols[1:]
return DataFrame(dummy_mat, index=index, columns=dummy_cols)
def get_empty_frame(data) -> DataFrame:
if isinstance(data, Series):
index = data.index
else:
index = np.arange(len(data))
return DataFrame(index=index)
def makeBindexDataCsv(cls,
cur=None,
start_date=None,
end_date=None,
basic_path=None,
output_file=None,
word_count=20,
stock_id=None,
ranking_type='tfidf'):
if cur == None or start_date == None or end_date == None or output_file == None or stock_id == None:
return None
if basic_path is None:
basic_path = os.path.dirname(os.path.abspath(__file__))
if word_count < 0:
word_count = 20
if ranking_type not in ["tfidf", "textrank"]:
ranking_type = "tfidf"
output_path = os.path.join(basic_path, output_file)
VTool.makeDirs(files=[output_path])
words = cls.getImportVocab(cur, count=20, ranking_type=ranking_type)
word_count = len(words)
for i in range(len(words)):
words[i] = "'" + words[i] + "'"
words_str = ",".join(words)
del words
word_key_list = []
for i in range(1, word_count + 1):
word_key_list.append("word%s" % i)
columns = [
"stock_id", "date", "opening", "closing", "difference",
"percentage_difference", "lowest", "highest", "volume", "amount",
"rate"
] + word_key_list
data = {}
for k in columns:
data[k] = []
pd.DataFrame(data).to_csv(output_path, index=False, columns=columns)
cur.execute(
"SELECT count(*) as count FROM history WHERE stock_id = '%s' and date between '%s' and '%s' "
% (stock_id, start_date, end_date))
count = cur.fetchall()
count = count[0][0]
skip = 50
slimit = 0
while slimit < count:
cur.execute(
"SELECT stock_id, opening, closing, difference, percentage_difference, lowest, highest, volume, amount, date FROM history WHERE stock_id = '%s' and date between '%s' and '%s' order by date asc, stock_id asc limit %d,%d "
% (stock_id, start_date, end_date, 0 if slimit - 1 < 0 else
slimit - 1, skip if slimit - 1 < 0 else skip + 1))
slimit += skip
history_tt = cur.fetchall()
history_t = []
for h in history_tt:
history_t.append([
int(h[0]),
float(h[1]),
float(h[2]),
float(h[3]),
float(h[4]),
float(h[5]),
float(h[6]),
float(h[7]),
float(h[8]),
str(h[9])
])
del history_tt
sdate = str(history_t[0][9])
edate = str(history_t[-1][9])
sdate = datetime.datetime.strptime(sdate, '%Y-%m-%d')
sdate = (sdate - datetime.timedelta(days=1)).strftime('%Y-%m-%d')
cur.execute(
"SELECT b.vocab_id, b.bindex, b.date FROM vocab v left join baidu_index b on v.id = b.vocab_id WHERE v.word in (%s) and b.date between '%s' and '%s' order by date, vocab_id asc"
% (words_str, sdate, edate))
bindex = cur.fetchall()
bindex_t = []
bindex_vec = 0
cur_date = None
if len(bindex) > 0:
cur_date = str(bindex[0][2])
bix = []
bix_item = [cur_date]
if len(bindex) > 0:
for bi in bindex:
if str(bi[2]) != cur_date:
cur_date = str(bi[2])
bix.append(bix_item)
bix_item = [cur_date]
bix_temp = json.loads(bi[1])
bix_item.append(bix_temp['all']['0'])
bix.append(bix_item)
del bindex
bindex = {}
for k in range(1, len(bix)):
b_t = []
for kk in range(1, len(bix[k])):
if int(bix[k][kk]) != 0 and int(bix[k - 1][kk]) != 0:
b_t.append(
str(
np.round(
float(100 * (int(bix[k][kk]) /
int(bix[k - 1][kk]) - 1)),
2)))
else:
b_t.append(str(0.01))
bindex[bix[k][0]] = b_t
del bix
for i in range(len(history_t)):
history_t[i] += bindex[history_t[i][9]]
history_temp = []
for h in zip(*history_t):
history_temp.append(h)
history = {
'stock_id': history_temp[0],
'opening': history_temp[1],
'closing': history_temp[2],
'difference': history_temp[3],
'percentage_difference': history_temp[4],
'lowest': history_temp[5],
'highest': history_temp[6],
'volume': history_temp[7],
'amount': history_temp[8],
'date': history_temp[9]
}
for i in range(10, 10 + word_count):
history["word%s" % (i - 9)] = history_temp[i]
del history_t, history_temp
history = DataFrame(history)
g_history = history.groupby(by=['stock_id'])
#0.01 -> 1 % 保留2位小数
history['rate'] = 100 * (g_history.shift(0)["closing"] /
g_history.shift(1)["closing"] - 1)
history.dropna(axis=0,
how='any',
thresh=None,
subset=None,
inplace=True)
for i in history.index:
history.loc[i, 'rate'] = str(
np.round(float(history['rate'][i]), 2))
#将经过标准化的数据处理成训练集和测试集可接受的形式
def func_train_data(data_stock):
if cls.groupby_skip == False:
cls.groupby_skip = True
return None
print("正在处理的股票代码:%06s" % data_stock.name)
data = {}
for k in columns:
data[k] = []
for i in range(len(data_stock) - 1):
for k in data:
data[k].append(data_stock.iloc[i][k])
pd.DataFrame(data).to_csv(output_path,
index=False,
header=False,
mode="a",
columns=columns)
g_stock = history.groupby(by=["stock_id"])
#清空接收路径下的文件，初始化列名
cls.groupby_skip = False
g_stock.apply(func_train_data)
def _get_dummies_1d(
data,
prefix,
prefix_sep="_",
dummy_na=False,
sparse=False,
drop_first=False,
dtype=None,
):
from pandas.core.reshape.concat import concat
# Series avoids inconsistent NaN handling
codes, levels = factorize_from_iterable(Series(data))
if dtype is None:
dtype = np.uint8
dtype = np.dtype(dtype)
if is_object_dtype(dtype):
raise ValueError("dtype=object is not a valid dtype for get_dummies")
def get_empty_frame(data) -> DataFrame:
if isinstance(data, Series):
index = data.index
else:
index = np.arange(len(data))
return DataFrame(index=index)
# if all NaN
if not dummy_na and len(levels) == 0:
return get_empty_frame(data)
codes = codes.copy()
if dummy_na:
codes[codes == -1] = len(levels)
levels = np.append(levels, np.nan)
# if dummy_na, we just fake a nan level. drop_first will drop it again
if drop_first and len(levels) == 1:
return get_empty_frame(data)
number_of_cols = len(levels)
if prefix is None:
dummy_cols = levels
else:
dummy_cols = [f"{prefix}{prefix_sep}{level}" for level in levels]
index: Optional[Index]
if isinstance(data, Series):
index = data.index
else:
index = None
if sparse:
fill_value: Union[bool, float, int]
if is_integer_dtype(dtype):
fill_value = 0
elif dtype == bool:
fill_value = False
else:
fill_value = 0.0
sparse_series = []
N = len(data)
sp_indices: List[List] = [[] for _ in range(len(dummy_cols))]
mask = codes != -1
codes = codes[mask]
n_idx = np.arange(N)[mask]
for ndx, code in zip(n_idx, codes):
sp_indices[code].append(ndx)
if drop_first:
# remove first categorical level to avoid perfect collinearity
# GH12042
sp_indices = sp_indices[1:]
dummy_cols = dummy_cols[1:]
for col, ixs in zip(dummy_cols, sp_indices):
sarr = SparseArray(
np.ones(len(ixs), dtype=dtype),
sparse_index=IntIndex(N, ixs),
fill_value=fill_value,
dtype=dtype,
)
sparse_series.append(Series(data=sarr, index=index, name=col))
out = concat(sparse_series, axis=1, copy=False)
return out
else:
dummy_mat = np.eye(number_of_cols, dtype=dtype).take(codes, axis=0)
if not dummy_na:
# reset NaN GH4446
dummy_mat[codes == -1] = 0
if drop_first:
# remove first GH12042
dummy_mat = dummy_mat[:, 1:]
dummy_cols = dummy_cols[1:]
return DataFrame(dummy_mat, index=index, columns=dummy_cols)
start_days)
else:
fitCurve(US_data[start_days:], title, 0, fill_dates, start_days)
pass
confirmed_cases_since_Jan_22 = [
1, 1, 2, 2, 5, 5, 5, 5, 5, 7, 8, 8, 11, 11, 11, 11, 11, 11, 11, 11, 12, 12,
13, 13, 13, 13, 13, 13, 13, 13, 15, 15, 15, 51, 51, 57, 58, 60, 68, 74, 98,
118, 149, 217, 262, 402, 518, 583, 959, 1281, 1663, 2179, 2727, 3499, 4632,
6421, 7783, 13677, 19100, 25489, 33276, 43847, 53740, 65778, 83836, 101657,
121478, 140886, 161807, 188172, 213372, 243453, 275586, 308850, 337072,
366614, 396263
] #Until April 7th
US_data = DataFrame({0: confirmed_cases_since_Jan_22})
ori_len = len(US_data)
start_days = 0
last_date = datetime.datetime(2020, 1,
22) + datetime.timedelta(days=(len(US_data) - 1))
last_date_str = last_date.strftime('%Y-%m-%d')
plotConfirmedCases(US_data, start_days, last_date_str)
fill_dates = 0
ratio = 1.0
US_data = fillData(US_data, fill_dates, ratio)
title = "US_best_scenario_pred"
go(start_days, fill_dates, ratio, US_data, title)
def makeOriginDataCsv(cls,
cur=None,
start_date=None,
end_date=None,
basic_path=None,
output_file=None,
stock_id=None):
#初始化源文件路径和存储文件路径
if cur is None or start_date is None or end_date is None or output_file is None or stock_id is None:
return None
if basic_path is None:
basic_path = os.path.dirname(os.path.abspath(__file__))
output_path = os.path.join(basic_path, output_file)
VTool.makeDirs(files=[output_path])
data = cur.execute(
"select id, stock_id, date, opening, closing, difference, percentage_difference, lowest, highest, volume, amount from history where stock_id = '%s' and date between '%s' and '%s' "
% (stock_id, start_date, end_date))
data = cur.fetchall()
if len(data) == 0:
return None
res = []
for d in data:
res.append([
int(d[0]),
int(d[1]),
str(d[2]),
float(d[3]),
float(d[4]),
float(d[5]),
float(d[6]),
float(d[7]),
float(d[8]),
float(d[9]),
float(d[10])
])
new_data = []
for d in zip(*res):
new_data.append(d)
origin_data = {
'id': new_data[0],
'stock_id': new_data[1],
'date': new_data[2],
'opening': new_data[3],
'closing': new_data[4],
'difference': new_data[5],
'percentage_difference': new_data[6],
'lowest': new_data[7],
'highest': new_data[8],
'volume': new_data[9],
'amount': new_data[10]
}
#读取原始数据，只保留需要使用的列
total_data = DataFrame(origin_data)
total_data.sort_values(by=['stock_id', 'date'], inplace=True)
#根据股票代码分组
g_stock_num = total_data.groupby(by=["stock_id"])
total_data["rate"] = 100 * (g_stock_num.shift(0)["closing"] /
g_stock_num.shift(1)["closing"] - 1)
for i in total_data.index:
total_data.loc[i, 'rate'] = str(
np.round(float(total_data['rate'][i]), 2))
#重新调整列的顺序，为接下来处理成输入、输出形式做准备
columns = [
"stock_id", "date", "opening", "closing", "difference",
"percentage_difference", "lowest", "highest", "volume", "amount",
"rate"
]
total_data = total_data[columns]
def func_train_data(data_one_stock_num):
if cls.groupby_skip == False:
cls.groupby_skip = True
return None
print("正在处理的股票代码:%06s" % data_one_stock_num.name)
data = {
"stock_id": [],
"date": [],
"opening": [],
"closing": [],
"difference": [],
"percentage_difference": [],
"lowest": [],
"highest": [],
"volume": [],
"amount": [],
"rate": []
}
for i in range(len(data_one_stock_num.index) - 1):
for k in data:
data[k].append(data_one_stock_num.iloc[i][k])
pd.DataFrame(data).to_csv(output_path,
index=False,
columns=columns)
total_data1 = total_data.dropna()
total_data2 = total_data1.drop(
total_data1[(total_data1.rate == 'nan')].index)
g_stock_num = total_data2.groupby(by=["stock_id"])
#清空接收路径下的文件，初始化列名
cls.groupby_skip = False
g_stock_num.apply(func_train_data)
