def execute(trial=False):
'''Run a statistical analysis gathering data comparing carbon efficacy to emissions per capita'''
startTime = datetime.datetime.now()
client = dml.pymongo.MongoClient()
repo = client.repo
repo.authenticate('aheckman_jfimbres', 'aheckman_jfimbres')
efficacy = repo.aheckman_jfimbres.carbon_efficacy.find({})
epc = repo.aheckman_jfimbres.emissions_per_capita.find({})
eff = t.project(efficacy, lambda x: x)
epc = t.project(epc, lambda x: x)
eff = [list(x.values()) for x in eff]
epc = [list(x.values()) for x in epc]
eff = eff[0][1:]
epc = epc[0][1:]
corr = scipy.stats.pearsonr(eff, epc)
corr = {"Stats": corr}
repo.dropCollection("Stats")
repo.createCollection("Stats")
repo['aheckman_jfimbres.Stats'].insert(corr)
repo.logout()
endTime = datetime.datetime.now()
return {"start": startTime, "end": endTime}
def execute(trial = False):
'''Return data that shows carbon efficacy alongside partisan climate opinion data'''
startTime = datetime.datetime.now()
client = dml.pymongo.MongoClient()
repo = client.repo
repo.authenticate('aheckman_jfimbres', 'aheckman_jfimbres')
efficacy = repo.aheckman_jfimbres.carbon_efficacy.find({})
opinions = repo.aheckman_jfimbres.partisan_map.find({})
state_ops = t.select(opinions, lambda x: x['GeoType'] == 'State')
ops_by_state = t.project(state_ops, lambda x: [x['GeoName'], x['Group'],x['TotalPop'], x['congress'], x['congressOppose'],
x['corporations'], x['corporationsOppose'], x['citizens'], x['citizensOppose'],
x['regulate'], x['regulateOppose'], x['exp'], x['expOppose'],
x['prienv'], x['prienvOppose'], x['happening'], x['happeningOppose'],
x['human'], x['humanOppose'], x['consensus'], x['consensusOppose'],
x['worried'], x['worriedOppose'], x['harmUS'], x['harmUSOppose']])
eff = t.project(efficacy, lambda x: x)
ops_w_eff = t.project(ops_by_state, lambda x: [x[0], (eff[0][x[0]], x[1:])])
ops_w_eff = t.aggregate(ops_w_eff, lambda x: [x[0], x[1][1]])
repo.dropCollection("opinion_by_efficacy")
repo.createCollection("opinion_by_efficacy")
repo['aheckman_jfimbres.opinion_by_efficacy'].insert(dict(ops_w_eff))
repo.logout()
endTime = datetime.datetime.now()
return {"start": startTime, "end": endTime}
def execute(trial = False):
'''Give the adjusted emissions per capita on a state-by-state basis'''
startTime = datetime.datetime.now()
client = dml.pymongo.MongoClient()
repo = client.repo
repo.authenticate('aheckman_jfimbres', 'aheckman_jfimbres')
co2_adjusted = repo.aheckman_jfimbres.co2_adjusted.find({})
c = repo.aheckman_jfimbres.census.find({})
adj = t.project(t.select(co2_adjusted, lambda x: x['State'] in list_of_states), lambda x: (x['State'], x['2016']*1000000))
pops = t.project(t.select(c, lambda x: x['NAME'] in list_of_states), lambda x: (x['NAME'], x['POPESTIMATE2017']))
# adj is given in x millions, so it needs to be scaled up to match population, which is just given in x
tons = t.aggregate(t.union(adj, pops), lambda vs: (vs[0]/vs[1]))
epc = dict(t.project(tons, lambda t: (t[0], t[1])))
repo.dropCollection("emissions_per_capita")
repo.createCollection("emissions_per_capita")
repo["aheckman_jfimbres.emissions_per_capita"].insert(epc)
repo.logout()
endTime = datetime.datetime.now()
return {"start":startTime, "end":endTime}
def execute(trial = False):
'''Find the efficiency of carbon usage on a stat-by-state basis'''
startTime = datetime.datetime.now()
client = dml.pymongo.MongoClient()
repo = client.repo
repo.authenticate('aheckman_jfimbres', 'aheckman_jfimbres')
co2_adjusted = repo.aheckman_jfimbres.co2_adjusted.find({})
co2_unadjusted = repo.aheckman_jfimbres.co2_unadjusted.find({})
carbon_intensity = repo.aheckman_jfimbres.carbon_intensity.find({})
adj = t.project(t.select(co2_adjusted, lambda x: x['State'] in list_of_states), lambda x: (x['State'], x['2016']))
unadj = t.project(t.select(co2_unadjusted, lambda x: x['State'] in list_of_states), lambda x: (x['State'], x['Total']))
intense = t.project(t.select(carbon_intensity, lambda x: x['State'] in list_of_states), lambda x: (x['State'], x['2016']))
emissions = t.aggregate(t.union(adj, unadj), np.mean)
efficacy = dict(t.aggregate(t.union(emissions, intense), lambda v: (v[0]/v[1])))
repo.dropCollection("carbon_efficacy")
repo.createCollection("carbon_efficacy")
repo['aheckman_jfimbres.carbon_efficacy'].insert(efficacy)
repo.logout()
endTime = datetime.datetime.now()
return {"start":startTime, "end":endTime}
def execute(trial=False):
'''Run a statistical analysis gathering data comparing carbon efficacy to emissions per capita'''
startTime = datetime.datetime.now()
client = dml.pymongo.MongoClient()
repo = client.repo
repo.authenticate('aheckman_jfimbres', 'aheckman_jfimbres')
ops_by_efficacy = repo.aheckman_jfimbres.opinion_by_efficacy.find({})
ops = t.project(ops_by_efficacy, lambda x: x)
ops = [list(x.values()) for x in ops]
ops = ops[0][1:]
#dem beliefs are ops[0][0][1]
#rep beliefs are ops[0][1]
q1 = []
q2 = []
q3 = []
q4 = []
q5 = []
q6 = []
q7 = []
q8 = []
q9 = []
q10 = []
q11 = []
for i in range(len(ops)):
q1 += ([ops[i][0][1][2],
ops[i][0][1][3]], [ops[i][1][2], ops[i][1][3]])
q2 += ([ops[i][0][1][4],
ops[i][0][1][5]], [ops[i][1][4], ops[i][1][5]])
q3 += ([ops[i][0][1][6],
ops[i][0][1][7]], [ops[i][1][6], ops[i][1][7]])
q4 += ([ops[i][0][1][8],
ops[i][0][1][9]], [ops[i][1][8], ops[i][1][9]])
q5 += ([ops[i][0][1][10],
ops[i][0][1][11]], [ops[i][1][10], ops[i][1][11]])
q6 += ([ops[i][0][1][12],
ops[i][0][1][13]], [ops[i][1][12], ops[i][1][13]])
q7 += ([ops[i][0][1][14],
ops[i][0][1][15]], [ops[i][1][14], ops[i][1][15]])
q8 += ([ops[i][0][1][16],
ops[i][0][1][17]], [ops[i][1][16], ops[i][1][17]])
q9 += ([ops[i][0][1][18],
ops[i][0][1][19]], [ops[i][1][18], ops[i][1][19]])
q10 += ([ops[i][0][1][20],
ops[i][0][1][21]], [ops[i][1][20], ops[i][1][21]])
q11 += ([ops[i][0][1][22],
ops[i][0][1][23]], [ops[i][1][22], ops[i][1][23]])
k1 = KMeans(n_clusters=2, random_state=0).fit(q1)
k2 = KMeans(n_clusters=2, random_state=0).fit(q2)
k3 = KMeans(n_clusters=2, random_state=0).fit(q3)
k4 = KMeans(n_clusters=2, random_state=0).fit(q4)
k5 = KMeans(n_clusters=2, random_state=0).fit(q5)
k6 = KMeans(n_clusters=2, random_state=0).fit(q6)
k7 = KMeans(n_clusters=2, random_state=0).fit(q7)
k8 = KMeans(n_clusters=2, random_state=0).fit(q8)
k9 = KMeans(n_clusters=2, random_state=0).fit(q9)
k10 = KMeans(n_clusters=2, random_state=0).fit(q10)
k11 = KMeans(n_clusters=2, random_state=0).fit(q11)
inertias = [
k1.inertia_, k2.inertia_, k3.inertia_, k4.inertia_, k5.inertia_,
k6.inertia_, k7.inertia_, k8.inertia_, k9.inertia_, k10.inertia_,
k11.inertia_
]
inertias = {"disagreement on each question": inertias}
repo.dropCollection("k_means")
repo.createCollection("k_means")
repo['aheckman_jfimbres.k_means'].insert(inertias)
repo.logout()
endTime = datetime.datetime.now()
return {"start": startTime, "end": endTime}
def execute(trial=False):
'''Run a statistical analysis gathering data comparing carbon efficacy to emissions per capita'''
startTime = datetime.datetime.now()
client = dml.pymongo.MongoClient()
repo = client.repo
repo.authenticate('aheckman_jfimbres', 'aheckman_jfimbres')
ops_by_efficacy = repo.aheckman_jfimbres.opinion_by_efficacy.find({})
ops = t.project(ops_by_efficacy, lambda x: x)
ops = [list(x.values()) for x in ops]
ops = ops[0][1:]
#dem beliefs are ops[0][0][1]
#rep beliefs are ops[0][1]
q1 = []
q2 = []
q3 = []
q4 = []
q5 = []
q6 = []
q7 = []
q8 = []
q9 = []
q10 = []
q11 = []
for i in range(len(ops)):
q1 += ([ops[i][0][1][2],
ops[i][0][1][3]], [ops[i][1][2], ops[i][1][3]])
q2 += ([ops[i][0][1][4],
ops[i][0][1][5]], [ops[i][1][4], ops[i][1][5]])
q3 += ([ops[i][0][1][6],
ops[i][0][1][7]], [ops[i][1][6], ops[i][1][7]])
q4 += ([ops[i][0][1][8],
ops[i][0][1][9]], [ops[i][1][8], ops[i][1][9]])
q5 += ([ops[i][0][1][10],
ops[i][0][1][11]], [ops[i][1][10], ops[i][1][11]])
q6 += ([ops[i][0][1][12],
ops[i][0][1][13]], [ops[i][1][12], ops[i][1][13]])
q7 += ([ops[i][0][1][14],
ops[i][0][1][15]], [ops[i][1][14], ops[i][1][15]])
q8 += ([ops[i][0][1][16],
ops[i][0][1][17]], [ops[i][1][16], ops[i][1][17]])
q9 += ([ops[i][0][1][18],
ops[i][0][1][19]], [ops[i][1][18], ops[i][1][19]])
q10 += ([ops[i][0][1][20],
ops[i][0][1][21]], [ops[i][1][20], ops[i][1][21]])
q11 += ([ops[i][0][1][22],
ops[i][0][1][23]], [ops[i][1][22], ops[i][1][23]])
k1 = KMeans(n_clusters=2, random_state=0).fit(q1)
k2 = KMeans(n_clusters=2, random_state=0).fit(q2)
k3 = KMeans(n_clusters=2, random_state=0).fit(q3)
k4 = KMeans(n_clusters=2, random_state=0).fit(q4)
k5 = KMeans(n_clusters=2, random_state=0).fit(q5)
k6 = KMeans(n_clusters=2, random_state=0).fit(q6)
k7 = KMeans(n_clusters=2, random_state=0).fit(q7)
k8 = KMeans(n_clusters=2, random_state=0).fit(q8)
k9 = KMeans(n_clusters=2, random_state=0).fit(q9)
k10 = KMeans(n_clusters=2, random_state=0).fit(q10)
k11 = KMeans(n_clusters=2, random_state=0).fit(q11)
inertias = [
k1.inertia_, k2.inertia_, k3.inertia_, k4.inertia_, k5.inertia_,
k6.inertia_, k7.inertia_, k8.inertia_, k9.inertia_, k10.inertia_,
k11.inertia_
]
'''questions = ['q1', 'q2', 'q3', 'q4', 'q5', 'q6', 'q7', 'q8', 'q9', 'q_10', 'q_11']
plt.figure()
plt.bar(questions, inertias)
plt.xlabel('Questions')
plt.ylabel('Total distance between agreement')
plt.title('Disagreement per question')
plt.show()'''
inertias = {"disagreement on each question": inertias}
questions = {
'Question 1': q1,
'Question 2': q2,
'Question 3': q3,
'Question 4': q4,
'Question 5': q5,
'Question 6': q6,
'Question 7': q7,
'Question 8': q8,
'Question 9': q9,
'Question 10': q10,
'Question 11': q11
}
repo.dropCollection("k_means")
repo.createCollection("k_means")
repo['aheckman_jfimbres.k_means'].insert(inertias)
repo.dropCollection("questions")
repo.createCollection("questions")
repo['aheckman_jfimbres.questions'].insert(questions)
repo.logout()
endTime = datetime.datetime.now()
return {"start": startTime, "end": endTime}
