#!/usr/bin/env python
# coding: utf-8

# ## collections_email

# In[1]:


import pandas as pd
import numpy as np

np.random.seed(24)
n = 5000
email = np.random.binomial(1, 0.5, n)

credit_limit = np.random.gamma(6, 200, n)
risk_score = np.random.beta(credit_limit, credit_limit.mean(), n)

opened = np.random.normal(5 + 0.001*credit_limit - 4*risk_score, 2)
opened = (opened > 4).astype(float) * email


agreement = np.random.normal(30 +(-0.003*credit_limit - 10*risk_score), 7) * 2 * opened
agreement = (agreement > 40).astype(float)

payments = (np.random.normal(500 + 0.16*credit_limit - 40*risk_score + 11*agreement + email, 75).astype(int) // 10) * 10

data = pd.DataFrame(dict(payments=payments,
                         email=email,
                         opened=opened,
                         agreement=agreement,
                         credit_limit=credit_limit,
                         risk_score=risk_score))

data.to_csv("collections_email.csv", index=False)


# ## hospital_treatment

# In[2]:


import pandas as pd
import numpy as np

np.random.seed(24)
n = 80

hospital = np.random.binomial(1, 0.5, n)

treatment = np.where(hospital.astype(bool),
                     np.random.binomial(1, 0.9, n),
                     np.random.binomial(1, 0.1, n))

severity = np.where(hospital.astype(bool), 
                    np.random.normal(20, 5, n),
                    np.random.normal(10, 5, n))

days = np.random.normal(15 + -5*treatment + 2*severity, 7).astype(int)

hospital = pd.DataFrame(dict(hospital=hospital,
                             treatment=treatment,
                             severity=severity,
                             days=days))

hospital.to_csv("hospital_treatment.csv", index=False)


# ## app engagement push

# In[3]:


import pandas as pd
import numpy as np

np.random.seed(24)
n = 10000

push_assigned = np.random.binomial(1, 0.5, n)

income = np.random.gamma(6, 200, n)

push_delivered = np.random.normal(5 + 0.3+income, 500)
push_delivered = ((push_delivered > 800) & (push_assigned == 1)).astype(int)

in_app_purchase = (np.random.normal(100 + 20*push_delivered + 0.5*income, 75).astype(int) // 10)

data = pd.DataFrame(dict(in_app_purchase=in_app_purchase,
                         push_assigned=push_assigned,
                         push_delivered=push_delivered))

data.to_csv("app_engagement_push.csv", index=False)


# ## Drug Impact

# In[17]:


import numpy as np
import pandas as pd

def make_confounded_data(N):

    def get_severity(df):
        return ((np.random.beta(1, 3, size=df.shape[0]) * (df["age"] < 30)) +
                (np.random.beta(3, 1.5, size=df.shape[0]) * (df["age"] >= 30)))

    def get_treatment(df):
        return ((.33 * df["sex"] +
                1.5 * df["severity"] +  df["severity"] ** 2 +
                0.15 * np.random.normal(size=df.shape[0])) > 1.5).astype(int)

    def get_recovery(df):
        return ((2 +
                0.5 * df["sex"] +
                0.03 * df["age"] + 0.03 * ((df["age"] * 0.1) ** 2) +
                df["severity"] + np.log(df["severity"]) +
                df["sex"] * df["severity"] -
                df["medication"]) * 10).astype(int)

    np.random.seed(1111)
    sexes = np.random.randint(0, 2, size=N)
    ages = np.random.gamma(8, scale=4, size=N)
    meds = np.random.beta(1, 1, size=N)

    # dados com designação aleatória
    df_rnd = pd.DataFrame(dict(sex=sexes, age=ages, medication=meds))
    df_rnd['severity'] = get_severity(df_rnd)
    df_rnd['recovery'] = get_recovery(df_rnd)

    features = ['sex', 'age', 'severity', 'medication', 'recovery']
    df_rnd = df_rnd[features]  # to enforce column order

    # dados observacionais
    df_obs = df_rnd.copy()
    df_obs['medication'] = get_treatment(df_obs)
    df_obs['recovery'] = get_recovery(df_obs)

    # dados contrafactuais data
    df_ctf = df_obs.copy()
    df_ctf['medication'] = ((df_ctf['medication'] == 1) ^ 1).astype(float)
    df_ctf['recovery'] = get_recovery(df_ctf)

    return df_rnd, df_obs, df_ctf

np.random.seed(1234)
df_rnd, df_obs, df_ctf = make_confounded_data(20000)

df_obs.to_csv("medicine_impact_recovery.csv", index=False)


# ## Bilboard Mkt

# In[5]:


import pandas as pd
import numpy as np
np.random.seed(123)
POAMay = np.random.gamma(7,10, 500) * np.random.binomial(1, .7, 500)
POAJul = np.random.gamma(7,15, 800) * np.random.binomial(1, .8, 800)
FLMay = np.random.gamma(10,20, 1300) * np.random.binomial(1, .85, 1300)
FLJul = np.random.gamma(11,21, 2000) * np.random.binomial(1, .9, 2000)

data = pd.concat([
    pd.DataFrame(dict(deposits = POAMay.astype(int), poa=1, jul=0)),
    pd.DataFrame(dict(deposits = POAJul.astype(int), poa=1, jul=1)),
    pd.DataFrame(dict(deposits = FLMay.astype(int), poa=0, jul=0)),
    pd.DataFrame(dict(deposits = FLJul.astype(int), poa=0, jul=1))
])
data.to_csv("billboard_impact.csv", index=False)


# In[ ]: