def add_day(df, countriez):
df_temp = df.copy()
df = pd.DataFrame(index=range(0, 100000))
for country in countriez:
data = (DplyFrame(df_temp) >> sift(X.country == country))
df_filt = (data >> mutate(day=range(1, len(data) + 1)))
df = pd.concat([df, df_filt], sort=False).dropna(how='all')
return df
def run_process(dat, cols, max_k, vis=0):
tod_result = pd.DataFrame()
info_result = pd.DataFrame()
#iterate from weekday, saturday and sunday (0,3)
for i in range(3):
temp = dat >> sift(X.DAY == i)
tod_result = tod_result.append(estimate_tod(temp, max_k))
info_result = info_result.append(tod_traffic_analyzer(i, temp, cols))
# if(vis == 1):
# print("Visualize the Silhouette score of day group (0:weekday, 1: sat, 2:sun)", i)
# visualize_tod(k)
return tod_result, info_result
def process_data(longform_df):
"""
Process data before beginning analysis.
Only going to focus on the actual match.
Doesn't make sense to consider the buildup & post-match here, since
we're focusing on the 'interruptions' that match events have that
should theoretically cause movement in search volume levels.
"""
stage_2_df = longform_df >> sift(X.stage_2_ind == 1)
stage_2_df = stage_2_df.reset_index(drop=True)
stage_2_df["date"] = stage_2_df.match_id.apply(
lambda x: "20" + x.split("20")[-1])
stage_2_df['date_time'] = (stage_2_df['date'].astype(str) + " " +
stage_2_df['time'].astype(str))
stage_2_df['date_time'] = pd.to_datetime(stage_2_df['date_time'],
errors="coerce",
infer_datetime_format=True)
return stage_2_df
# longform_df.competitive_idx)
#
# model = ARIMA(endog=longform_df.shorthand_search_vol,
# exog=x_mat,
# dates=longform_df.date_time,
# order=(2, 0, 2))
#
# model_fit = model.fit(disp=0) # disp=0 turns off debug information
# with open('model2.txt', 'w') as f:
# # print summary
# print >> f, model_fit.summary()
# ARIMA MODEL #3: STAGE 2, MATCH EVENTS ONLY
# LET'S ONLY FOCUS ON STAGE 2...makes more sense to consider match events in the context of the match itself,
# and not the buildup or post-match reaction time...
stage_2_df = longform_df >> sift(X.stage_2_ind == 1)
stage_2_df = stage_2_df.reset_index(drop=True)
# new, more thoughtful ARIMA model parameters
# d = 1 ("first difference"); let's predict the delta b/w volumes at consecutive intervals
# aka, "stationarizing" the time series
# q = 1 (a series displays moving average behavior if it apparently undergoes random
# "shocks" whose effects are felt in 2+ consecutive periods. )
# TODO, diff b/w q = 1 & q = 2?
x_mat = stage_2_df >> select(stage_2_df.home_goal, stage_2_df.away_goal,
stage_2_df.home_yellow, stage_2_df.away_yellow,
stage_2_df.home_red, stage_2_df.away_red,
stage_2_df.competitive_idx)
model = ARIMA(endog=stage_2_df.shorthand_search_vol,
import dplython as dp
iris = dp.DplyFrame(iris)
from dplython import (DplyFrame, X, diamonds, select, sift,
sample_n, sample_frac, head, arrange, mutate, group_by,
summarize, DelayFunction)
# data(iris)
# data=iris %>%
# select(Petal.Length, Petal.Width, Sepal.Length, Sepal.Width, Species)
iris >> dp.select(X.Species) >> dp.head()
iris[['Species', 'PetalLength']]
iris.drop('SepalLength', axis=1) #quitar esa columna
iris.drop(5, axis=0) #quitar la sexta fila
# data=iris %>%
# filter(Petal.Length>1 & Petal.Length<100)
iris >> dp.sift(X.PetalLength>5)
iris[(iris['PetalLength']>5) & (iris['PetalLength']<6)]
# data=iris %>%
# dplyr::group_by(Species) %>%
# summarise(media=mean(Petal.Length))
iris >> dp.group_by(X.Species) >> dp.summarize(media=X.PetalLength.mean())
iris.groupby(['Species'])['PetalLength'].agg(['mean', 'sum', 'count'])
iris.groupby(['Species'])['PetalLength'].agg({'var1':'mean', 'var2':'sum', 'var3':'count'})
iris.groupby(['Species'])['PetalLength'].agg({'var1':['mean', 'sum']})
aggregations = {
'dsuma':'sum',
}
import math
def main(argv):
yURL = None
outdir = None
maxFrames = 500
yURL = input("Enter the youtube url:")
outdir = input("Enter the output directory:")
maxFrames = int(input("Enter the maximum number of frames to check:"))
faceDet = cv2.CascadeClassifier(
"haarcascade/haarcascade_frontalface_default.xml")
faceDet2 = cv2.CascadeClassifier(
"haarcascade/haarcascade_frontalface_alt2.xml")
faceDet3 = cv2.CascadeClassifier(
"haarcascade/haarcascade_frontalface_alt.xml")
faceDet4 = cv2.CascadeClassifier(
"haarcascade/haarcascade_frontalface_alt_tree.xml")
#
pdata, pframes, pfacedims = getNewInstances(yURL,
faceDet,
faceDet2,
faceDet3,
faceDet4,
maxCount=maxFrames)
#
headers = dict()
headers['Ocp-Apim-Subscription-Key'] = ms_key1
headers['Content-Type'] = 'application/octet-stream'
#
resultsDf = pd.DataFrame()
frameId = 0
for image in pframes:
print("posting frame %d of %d" % (frameId, len(pframes)))
#sending the frame image to MS cognitive services
resultMS = processRequest(image, headers)
#isinstance == type()
if isinstance(resultMS, list):
for result in resultMS:
if isinstance(result, dict):
resFrameList = []
for res in result['scores'].items():
resFrameList.append(
(frameId, res[0], res[1],
result["faceRectangle"]['left'],
result["faceRectangle"]['top'],
result["faceRectangle"]['width'],
result["faceRectangle"]['height']))
appendDf = pd.DataFrame(resFrameList,
columns=[
"frameId", "emotionLabel",
"conf", "faceleft",
"facetop", "faceW", "faceH"
])
resultsDf = resultsDf.append(appendDf)
time.sleep(2)
frameId += 1
#
# print(resultsDf)
#we append all the data to the dataframe
#http://bluescreen.club/2017/06/18/import-pandas-as-pd/
#then we convert the dataframe to a Dplyframe object which allows us to do higher level data analytics
#for this one, we will select out the top most ranking face frames for each of the emotions
#microsoft provides us with around 8 emotions
#so we sort out 8 faces for 8 emotions and then save them accordingly
dfFaces = DplyFrame(resultsDf)
# print(dfFaces)
topFaces = (
dfFaces >> group_by(X.emotionLabel) >> sift(X.conf == X.conf.max()) >>
sift(X.frameId == X.frameId.min()) >> ungroup() >> group_by(
X.frameId) >> sift(X.conf == X.conf.max()) >> ungroup() >> arrange(
X.emotionLabel))
topFaces = topFaces.drop_duplicates()
#print(topFaces)
i = 0
for index, row in topFaces.iterrows():
print("saving emotion frame %d of %d" % (i, len(topFaces.index)))
#
emotion = row["emotionLabel"]
confid = int(row["conf"] * 100)
image = pframes[int(row["frameId"])]
faceL = row["faceleft"]
faceT = row["facetop"]
faceW = row["faceW"]
faceH = row["faceH"]
#save cropped face
imageW = image[faceT:faceT + faceH, faceL:faceL + faceW]
cv2.imwrite(
os.path.expanduser("%s/Cropped_%s.jpg" % (outdir, emotion)),
imageW)
#if you wish to put a rectangle on the faces then uncomment below
#
# cv2.rectangle( image,(faceL,faceT),
# (faceL+faceW, faceT + faceH),
# color = (255,0,0), thickness = 5 )
# cv2.putText( image, emotion, (faceL,faceT-10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255,0,0), 1 )
#
cv2.imwrite(os.path.expanduser("%s/%s.jpg" % (outdir, emotion)), image)
i += 1
# Extending dfply with custom functions
# https://github.com/kieferk/dfply/blob/master/examples/basics-extending-functionality.ipynb
############### dplython #################
from dplython import (DplyFrame, X, diamonds, select, sift,
sample_n, sample_frac, head, arrange, mutate, group_by,
summarize, DelayFunction)
df = DplyFrame(df)
df >> head(5)
df >> sample_n(5)
df >> select(X.name, X.category, X.country, X.role, X.description)
df >> sift(X.category == 'Leadership') # As in pandas, use bitwise logical operators like |, & (, is same as &)
df >> arrange(X.country) # couldnt find a way to sort descending so moved to dfply library
df >> mutate(carat_bin=X.carat.round())
df >> group_by(X.category) >> summarize(num_of_people = X.name.count())
# It's possible to pass the entire dataframe using X._
# The special Later name, "_" will refer to the entire DataFrame.
# Combine multiple
(df >> sift(X.name != 'Unsung hero')
>> group_by(X.category)
>> summarize(num_of_people = X.name.count())
).set_index('category').plot(title='# of Women Recognized by Category', y='num_of_people', ylabel='', legend=False, kind='pie')
denominator = np.max(data, 0) - np.min(data, 0)
return numerator / (denominator + 1e-7)
# train Parameters
seq_length = 60
data_dim = 8
hidden_dim = 10
output_dim = 1
learning_rate = 0.01
iterations = 500
# last, diff_24h, diff_per_24h, bid, ask, low, high, volume
data = DplyFrame(pd.read_csv('./bitcoin_ticker.csv', delimiter=','))
data = data >> sift(X.rpt_key == 'btc_krw') >> select(
X.last, X.diff_24h, X.diff_per_24h, X.bid, X.ask, X.low, X.high, X.volume)
data = np.asarray(data)
#data = MinMaxScaler(data)
data = tf.layers.batch_normalization(data)
x = data
y = data[:, [0]] # last as label
# build a dataset
dataX = []
dataY = []
for i in range(0, len(y) - seq_length):
_x = x[i:i + seq_length]
_y = y[i + seq_length] # Next close price
print(_x, "->", _y)
dataX.append(_x)
plt.tight_layout(pad = 0)
plt.show()
"""stacked bar plot"""
dfx = (dfr >>
arrange(-X.tot))
dfx=dfx.head(50)
from plotnine import *
(ggplot(dfx, aes(x='word', y='tot', fill='source'))
+ geom_col() +
theme(axis_text_x=element_text(rotation=45, hjust=1))
)
"""each newspaper"""
dfr = DplyFrame(output)
df_tele =(dfr >>sift(X.source=="guardian"))
df_tele = (df_tele >>
group_by(X.word, X.source) >>
summarize(tot=X.count.sum()))
df_tele = (df_tele >>select(X.word, X.tot ))
d = {}
for a, x in dff.values:
d[a] = x
wordcloud = WordCloud(width = 1000, height = 1000,
background_color ='white',
min_font_size =10, max_font_size=150).generate_from_frequencies(frequencies=d)
# plot the WordCloud image
plt.figure(figsize = (8, 8), facecolor = None)
plt.imshow(wordcloud)
def czMatchmaker(data, Q, precursor_fasta):
data = pd.read_csv(
"/Users/matteo/Documents/czMatchmaker/data/examplaryData.csv")
data = DplyFrame(data)
precursors = data >> \
sift( X.tag == 'precursor' ) >> \
select( X.active, X.neutral, X.estimates)
fragments = data >> sift( X.tag != 'precursor' ) >> \
group_by( X.tag, X.active, X.broken_bond ) >> \
summarize( estimates = X.estimates.sum() )
I_on_fragments = {}
optiminfos = {}
for break_point, data in fragments.groupby('broken_bond'):
pairing, optiminfo = collect_fragments(data, Q)
I_on_fragments[break_point] = pairing
optiminfos[break_point] = optiminfo
cations_fragmented_I = sum(
sum(I_on_fragments[bP][p] for p in I_on_fragments[bP])
for bP in I_on_fragments)
I_no_reactions = precursors >> \
sift( X.active==Q, X.neutral == 0) >> \
select( X.estimates )
I_no_reactions = I_no_reactions.values.flatten()[0]
prec_ETnoD_PTR_I = precursors >> \
sift( X.active != Q ) >> \
rename( ETnoD = X.neutral, I = X.estimates ) >> \
mutate( PTR = Q - X.ETnoD - X.active ) >> \
select( X.ETnoD, X.PTR, X.I )
I_prec_no_frag = prec_ETnoD_PTR_I >> \
summarize( I = X.I.sum() )
I_prec_no_frag = I_prec_no_frag.values.flatten()[0]
precursorNoReactions = precursors >> \
sift( X.active == Q ) >> \
select( X.estimates )
prec_ETnoD_PTR_I = prec_ETnoD_PTR_I >> mutate(
I_PTR = crossprod(X.PTR, X.I), \
I_ETnoD = crossprod(X.ETnoD, X.I) ) >> \
summarize( I_PTR = X.I_PTR.sum(), I_ETnoD = X.I_ETnoD.sum() )
I_PTR_no_frag, I_ETnoD_no_frag = prec_ETnoD_PTR_I.values.flatten()
prob_PTR = I_PTR_no_frag / (I_PTR_no_frag + I_ETnoD_no_frag)
prob_ETnoD = 1. - prob_PTR
I_frags = dict(
(bP, sum(I_on_fragments[bP][pairing]
for pairing in I_on_fragments[bP])) for bP in I_on_fragments)
I_frag_total = sum(I_frags[bP] for bP in I_frags)
prob_frag = Counter(
dict((int(bP), I_frags[bP] / I_frag_total) for bP in I_frags))
prob_frag = [prob_frag[i] for i in range(len(precursor_fasta))]
I_frags_PTRETnoD_total = sum(
(Q - 1 - sum(q for cz, q in pairing)) * I_on_fragments[bP][pairing]
for bP in I_on_fragments for pairing in I_on_fragments[bP])
anion_meets_cation = I_frags_PTRETnoD_total + I_PTR_no_frag + I_ETnoD_no_frag
prob_fragmentation = I_frags_PTRETnoD_total / anion_meets_cation
prob_no_fragmentation = 1 - prob_fragmentation
prob_no_reaction = I_no_reactions / (I_no_reactions + I_frag_total +
I_prec_no_frag)
prob_reaction = 1. - prob_no_reaction
res = {}
res['reaction'] = (prob_reaction, prob_no_reaction)
res['fragmentation'] = (prob_fragmentation, prob_no_fragmentation)
res['fragmentation_amino_acids'] = tuple(prob_frag)
return res
start_time = time.clock()
dt = d0.ply_where( X.usertype == 'Subscriber' ).ply_select(
slat = X.latitude_start * math.pi / 180,
elat = X.latitude_end * math.pi / 180,
slng = X.longitude_start * math.pi / 180,
elng = X.longitude_end * math.pi / 180
)
print( 'pandas_ply: ' + str( round( time.clock() - start_time, 2 ) ) + ' seconds.' )
# dplython
import pandas
from dplython import (DplyFrame, X, diamonds, select, sift, sample_n,
sample_frac, head, arrange, mutate, group_by, summarize, DelayFunction)
start_time = time.clock()
dt = DplyFrame(d0) >> sift( X.usertype == 'Subscirber' ) >> mutate(
slat = X.latitude_start * math.pi / 180,
elat = X.latitude_end * math.pi / 180,
slng = X.longitude_start * math.pi / 180,
elng = X.longitude_end * math.pi / 180
)
print( 'dplython: ' + str( round( time.clock() - start_time, 2 ) ) + ' seconds.' )
# dfply
from dfply import *
import pandas as pd
start_time = time.clock()
dt =d0 >> mask( X.usertype == 'Subscirber' ) >> mutate(
slat = X.latitude_start * math.pi / 180,
elat = X.latitude_end * math.pi / 180,
import pandas
from dplython import (DplyFrame, X, diamonds, select, sift, sample_n,
sample_frac, head, arrange, mutate, group_by, summarize,
DelayFunction)
diamonds >> head(5)
diamonds >> select(X.carat, X.cut, X.price) >> head(5)
d = (diamonds >> sift(X.carat > 4) >> select(X.carat, X.cut, X.depth, X.price)
>> head(2))
(diamonds >> mutate(carat_bin=X.carat.round()) >> group_by(X.cut, X.carat_bin)
>> summarize(avg_price=X.price.mean()))
test = df['deaths'] < 0
less_than_zero = df[test]
print(less_than_zero.shape)
print(less_than_zero.head())
test
#df['deaths_fixed'] = df['deaths_new'].apply(lambda x: 'True' if x <= 0 else 'False')
def load_data(input_dir, crsrd_id):
cctv_log = pd.read_csv(input_dir + "/ORT_CCTV_5MIN_LOG.csv")
cctv_mst = pd.read_csv(input_dir + "/ORT_CCTV_MST.csv")
cctv_log['DATE'] = pd.DataFrame(pd.DatetimeIndex(cctv_log['REG_DT']).date)
cctv_log['HOUR'] = pd.DataFrame(pd.DatetimeIndex(cctv_log['REG_DT']).hour)
cctv_log['MINUTE'] = (
pd.DataFrame(pd.DatetimeIndex(cctv_log['REG_DT']).minute) // 30) * 30
cctv_log['temp_DAY'] = pd.to_datetime(cctv_log['DATE']).dt.dayofweek
cctv_log.loc[cctv_log['temp_DAY'] < 5, 'DAY'] = int(0) #mon - fri
cctv_log.loc[cctv_log['temp_DAY'] == 5, 'DAY'] = int(1) #sat
cctv_log.loc[cctv_log['temp_DAY'] == 6, 'DAY'] = int(2) #sun
df0 = DplyFrame(cctv_log) >> group_by(
X.DATE, X.DAY, X.HOUR, X.MINUTE, X.CCTV_ID) >> summarize(
GO_TRF=X.GO_BIKE.sum() + X.GO_CAR.sum() + X.GO_SUV.sum() +
X.GO_VAN.sum() + X.GO_TRUCK.sum() + X.GO_BUS.sum() +
X.RIGHT_BIKE.sum() + X.RIGHT_CAR.sum() + X.RIGHT_SUV.sum() +
X.RIGHT_VAN.sum() + X.RIGHT_TRUCK.sum() + X.RIGHT_BUS.sum(),
LEFT_TRF=X.LEFT_BIKE.sum() + X.LEFT_CAR.sum() + X.LEFT_SUV.sum() +
X.LEFT_VAN.sum() + X.LEFT_TRUCK.sum() + X.LEFT_BUS.sum())
# Extract records of selected crossroad
cctv_mst = DplyFrame(cctv_mst) >> sift(X.CRSRD_ID == crsrd_id) >> select(
X.CRSRD_ID, X.CCTV_ID)
df0 = pd.merge(df0, cctv_mst, how="inner", on="CCTV_ID")
df0 = df0.sort_values(['DATE', 'HOUR', 'MINUTE', 'CCTV_ID'])
# Time frame from existing dataset
tf = DplyFrame(
df0.drop_duplicates(
['DATE', 'DAY', 'HOUR', 'MINUTE'], keep='last')) >> select(
X.DATE, X.DAY, X.HOUR, X.MINUTE)
# Process the datastructure into pivot
cctv_list = sorted(cctv_mst['CCTV_ID'].unique())
df1 = tf
for cctv in cctv_list:
a = df0 >> sift(X.CCTV_ID == cctv) >> select(
X.DATE, X.DAY, X.HOUR, X.MINUTE, X.GO_TRF, X.LEFT_TRF)
df1 = pd.merge(df1,
a,
how='left',
on=['DATE', 'DAY', 'HOUR', 'MINUTE'],
suffixes=('', '_' + str(cctv)))
df1 = df1.set_index(['DATE', 'DAY', 'HOUR', 'MINUTE'])
df1 = df1.fillna(df1.rolling(window=24, min_periods=1, center=True).mean())
df1 = df1.fillna(0)
df1 = df1.reset_index()
df1['TOTAL_TRF'] = DplyFrame(df1.iloc[:, 4:3 + len(cctv_list) * 2].sum(
axis=1, skipna=True))
df1 = df1 >> sift(X.TOTAL_TRF > 0)
print(df1)
# Name the cctv id and direction - for tod_traffic_analyzer
cols = [cctv + '_GO_RATE' for cctv in cctv_list]
cols.extend([cctv + '_LEFT_RATE' for cctv in cctv_list])
cols = sorted(cols)
cols = ['TOD'] + cols + ['TOTAL_TRF']
return df1, cols
def main(argv):
ytURL = None
outdir = None
maxFrames = 500
try:
opts, args = getopt.getopt(argv, "hy:o:m:",
["yturl=", "odir=", "maxframes="])
except getopt.GetoptError:
print 'Error: shellScript.py -y <yturl> -o <odir> -m <maxframes>'
sys.exit(2)
#print opts
for opt, arg in opts:
if opt == '-h':
print 'help: shellScript.py -y <yturl> -o <odir> -m <maxframes>'
sys.exit()
elif opt in ("-y", "--yturl"):
print("--yturl={}".format(arg))
ytURL = arg
elif opt in ("-o", "--odir"):
print("--odir={}".format(arg))
outdir = arg
elif opt in ("-m", "--maxframes"):
print("--maxframes={}".format(arg))
maxFrames = int(arg)
#
if ytURL is None:
print 'bad yt: shellScript.py -y <yturl> -o <odir> -m <maxframes>'
sys.exit()
#
if outdir is None:
print 'bad outdir: shellScript.py -y <yturl> -o <odir> -m <maxframes>'
sys.exit()
#
if False == isinstance(maxFrames, (int, long)):
print 'bad maxFrames: shellScript.py -y <yturl> -o <odir> -m <maxframes>'
sys.exit()
#
#
faceDet = cv2.CascadeClassifier(
"haarcascade/haarcascade_frontalface_default.xml")
faceDet2 = cv2.CascadeClassifier(
"haarcascade/haarcascade_frontalface_alt2.xml")
faceDet3 = cv2.CascadeClassifier(
"haarcascade/haarcascade_frontalface_alt.xml")
faceDet4 = cv2.CascadeClassifier(
"haarcascade/haarcascade_frontalface_alt_tree.xml")
#
pdata, pframes, pfacedims = getNewInstances(ytURL,
faceDet,
faceDet2,
faceDet3,
faceDet4,
maxCount=maxFrames)
#
headers = dict()
headers['Ocp-Apim-Subscription-Key'] = ms_key1
headers['Content-Type'] = 'application/octet-stream'
#
resultsDf = pd.DataFrame()
frameId = 0
for image in pframes:
print("posting frame %d of %d" % (frameId, len(pframes)))
resultMS = processRequest(image, headers)
#
if isinstance(resultMS, list):
for result in resultMS:
if isinstance(result, dict):
resFrameList = []
for res in result['scores'].items():
resFrameList.append(
(frameId, res[0], res[1],
result["faceRectangle"]['left'],
result["faceRectangle"]['top'],
result["faceRectangle"]['width'],
result["faceRectangle"]['height']))
appendDf = pd.DataFrame(resFrameList,
columns=[
"frameId", "emotionLabel",
"conf", "faceleft",
"facetop", "faceW", "faceH"
])
resultsDf = resultsDf.append(appendDf)
time.sleep(2)
frameId += 1
#
dfFaces = DplyFrame(resultsDf)
#
topFaces = (
dfFaces >> group_by(X.emotionLabel) >> sift(X.conf == X.conf.max()) >>
sift(X.frameId == X.frameId.min()) >> ungroup() >> group_by(
X.frameId) >> sift(X.conf == X.conf.max()) >> ungroup() >> arrange(
X.emotionLabel))
topFaces = topFaces.drop_duplicates()
#print(topFaces)
#
i = 0
for index, row in topFaces.iterrows():
print("saving emotion frame %d of %d" % (i, len(topFaces.index)))
#
emotion = row["emotionLabel"]
confid = int(row["conf"] * 100)
image = pframes[int(row["frameId"])]
faceL = row["faceleft"]
faceT = row["facetop"]
faceW = row["faceW"]
faceH = row["faceH"]
#
#save cropped face
imageW = image[faceT:faceT + faceH, faceL:faceL + faceW]
cv2.imwrite(
os.path.expanduser("%s/Cropped_%s.jpg" % (outdir, emotion)),
imageW)
#
cv2.rectangle(image, (faceL, faceT), (faceL + faceW, faceT + faceH),
color=(255, 0, 0),
thickness=5)
cv2.putText(image, emotion, (faceL, faceT - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 0, 0), 1)
#
cv2.imwrite(os.path.expanduser("%s/box%s.jpg" % (outdir, emotion)),
image)
i += 1
'away_yellows': away_yellows,
'home_reds': home_reds,
'away_reds': away_reds})
df_container.append(data)
# concatenate all into one master data frames & generate descriptive stats
master_df = DplyFrame(pd.concat(df_container))
print("home goals", "\n", master_df.home_goals.describe())
print("away goals", "\n", master_df.away_goals.describe())
print("home yellows", "\n", master_df.home_yellows.describe())
print("away yellows", "\n", master_df.away_yellows.describe())
print("home reds", "\n", master_df.home_reds.describe())
print("away reds", "\n", master_df.away_reds.describe())
print("frequency of home goals", len(master_df >> sift(X.home_goals > 0)))
print("frequency of away goals", len(master_df >> sift(X.away_goals > 0)))
print("frequency of home yellows", len(master_df >> sift(X.home_yellows > 0)))
print("frequency of away yellows", len(master_df >> sift(X.away_yellows > 0)))
print("frequency of home reds", len(master_df >> sift(X.home_reds > 0)))
print("frequency of away reds", len(master_df >> sift(X.away_reds > 0)))
goals = master_df.apply(lambda row: row.home_goals + row.away_goals, axis=1)
print("goals", goals.describe())
print("freq", len(goals.nonzero()[0]))
yellows = master_df.apply(lambda row: row.home_yellows + row.away_yellows, axis=1)
print("yellows", yellows.describe())
print("yellows", len(yellows.nonzero()[0]))
reds = master_df.apply(lambda row: row.home_reds + row.away_reds, axis=1)
