In [151]:
%matplotlib inline
import pandas as pd
import matplotlib.pyplot as plt
from numpy import nan
plt.style.use('ggplot')
In [ ]:
In [152]:
from IPython.core.display import HTML
css = open('style-table.css').read() + open('style-notebook.css').read()
HTML('<style>{}</style>'.format(css))
Out[152]:
In [ ]:
In [12]:
# Carpeta Base de Datos Faltantes _ X
# Carga de datos
## Por el momento todos los archivos no se encuentran disponibles para descargar
In [13]:
#Cargar archivo 1 (DISCO2-TR_EXP_ALUMNO_CONTROL.txt)
#Intenté estrategia whitespace pero hay columnas vacías y campos con espacios intermedios (falta1 y falta2)
In [14]:
faltante1 = pd.read_csv("/Users/luis/Desktop/CEMABE/BDfaltantes_X/DISCO2-TR_EXP_ALUMNO_CONTROL.txt", sep='\t', header=0, encoding='latin-1', low_memory=False)
faltante1.head()
Out[14]:
In [15]:
faltante2 = pd.read_csv("/Users/luis/Desktop/CEMABE/BDfaltantes_X/DISCO2-TR_EXP_CUES_CONAFE_ALUMNO.txt", header=0, encoding='latin-1', sep='\t', low_memory=False)
faltante2.head()
Out[15]:
In [16]:
faltante3 = pd.read_csv("/Users/luis/Desktop/CEMABE/BDfaltantes_X/DISCO3-TR_EXP_CUES_ALUMNO.txt", sep='|', header=0, encoding='latin-1')
faltante3.head()
Out[16]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [17]:
# Carpeta Centros_trabajo_X
# Carga de datos
## Por el momento todos los archivos no se encuentran disponibles para descargar
In [18]:
centrost1 = pd.read_csv("/Users/luis/Desktop/CEMABE/Centros_trabajo_X/TR_EXP_CENTRAB_CONTROL.txt", header=0, sep='|', encoding='latin-1', index_col=0)
centrost1.head()
Out[18]:
In [19]:
centrost2 = pd.read_csv("/Users/luis/Desktop/CEMABE/Centros_trabajo_X/TR_EXP_CUES_CENTRAB.txt", header=0, sep='|', encoding='latin-1')
centrost2.head()
Out[19]:
In [ ]:
In [20]:
centrost3 = pd.read_csv("/Users/luis/Desktop/CEMABE/Centros_trabajo_X/TR_EXP_CUES_CONAFE_INM_CT_LST.txt", header=0, sep='|', encoding='latin-1')
centrost3.head()
Out[20]:
In [ ]:
In [21]:
centrost4 = pd.read_csv("/Users/luis/Desktop/CEMABE/Centros_trabajo_X/TR_EXP_REL_GRADOS_GRUPOS_CT.txt", header=0, sep='|', encoding='latin-1')
centrost4.head()
Out[21]:
In [ ]:
In [22]:
# Carpeta Inmueble (3 archivos)
# Carga de datos
## Por el momento todos los archivos no se encuentran disponibles para descargar
In [ ]:
In [23]:
inmueble1 = pd.read_csv("/Users/luis/Desktop/CEMABE/Inmueble/TR_EXP_CUES_INMUEBLE.txt", header=0, sep='|', encoding='latin-1')
inmueble1.head()
Out[23]:
In [ ]:
In [24]:
inmueble2 = pd.read_csv("/Users/luis/Desktop/CEMABE/Inmueble/TR_EXP_INMUEBLE_CONTROL.txt", header=0, sep='|', encoding='latin-1', low_memory=False)
inmueble2.head()
Out[24]:
In [25]:
inmueble3 = pd.read_csv("/Users/luis/Desktop/CEMABE/Inmueble/TR_EXP_CUES_CONAFE_INM_CT.txt", header=0, sep='|', encoding='latin-1', low_memory=False, error_bad_lines=False, warn_bad_lines=True)
inmueble3.head()
Out[25]:
In [ ]:
In [26]:
# Carpeta personal
# Cargar datos
In [27]:
personal1 = pd.read_csv("/Users/luis/Desktop/CEMABE/Personal/TR_EXP_ACTIVIDADES_ACADEMICOS.txt", header=0, sep='|', encoding='latin-1')
personal1.head()
Out[27]:
In [ ]:
In [28]:
personal2 = pd.read_csv("/Users/luis/Desktop/CEMABE/Personal/TR_EXP_CUES_CONAFE_PERSONAL.txt", header=0, sep='|', encoding='latin-1')
personal2.head()
Out[28]:
In [ ]:
In [29]:
personal3 = pd.read_csv("/Users/luis/Desktop/CEMABE/Personal/TR_EXP_CUES_PERSONAL_PLAZA.txt", header=0, sep='|', encoding='latin-1', error_bad_lines=False, warn_bad_lines=True)
personal3.head()
Out[29]:
In [ ]:
In [30]:
personal4 = pd.read_csv("/Users/luis/Desktop/CEMABE/Personal/TR_EXP_CUES_PERSONAL.txt", header=0, sep='|', encoding='latin-1', error_bad_lines=False, warn_bad_lines=True)
personal4.head()
Out[30]:
In [ ]:
In [31]:
personal5 = pd.read_csv("/Users/luis/Desktop/CEMABE/Personal/TR_EXP_MATERIAS_MAESTROS.txt", header=0, sep='|', encoding='latin-1', error_bad_lines=False, warn_bad_lines=True)
personal5.head()
Out[31]:
In [ ]:
In [32]:
personal6 = pd.read_csv("/Users/luis/Desktop/CEMABE/Personal/TR_EXP_PERSONAL_CONTROL.txt", header=0, sep='|', encoding='latin-1', error_bad_lines=False, warn_bad_lines=True)
personal6.head()
Out[32]:
In [ ]:
In [33]:
personal7 = pd.read_csv("/Users/luis/Desktop/CEMABE/Personal/TR_EXP_PLAZAS.txt", header=0, sep='|', encoding='latin-1', error_bad_lines=False, warn_bad_lines=True)
personal7.head()
Out[33]:
In [ ]:
#Transformaciones
##Diccionarios
sustituciones = {
'P3': {1: 11, 2: 8, 3: 3, 4:0, 5: 0},
'P11': {0: 1, 1: 1}, #.get(key, 0) #>1
'P13A': {1: 1.5, 2: 1, 3: 1, 4: 0, 5: 0},
'P14': {1: 3, 2: 2, 3: 0, 4: 0, 5: 0, 6: 0},
'P15': {1: 3, 2: 2, 3: 2, 4: 0, 5: 0, 6: 0},
'P16': {1: 3, 2: 2, 3: 0},
'P17A': {1: 3, 2: 2, 3: 2, 4: 0, 5: 1, 6: 0},
'P18A': {1: 3, 2: 2, 3: 2, 4: 1, 5: 0},
'P19': {1: 1, 2: 0},
'P20': {1: 3, 2:0},
'P21': {1: 3, 2:0},
'P22': {1: 3, 2:0},
'P23': {1: 5.5, 2:0},
'P24': {1: 5.5, 2:0},
'P25': {0: 0, 1: 0.5, 2: 1,}#.get(key, 1) #2+: 1
'P26': {0: 0, 1: 1}#.get(key, 0) #1+: 1
'P27': {0: 0, 1: 1}#.get(key, 0) #1+: 1
'P28': {0: 0.3, 1: 0}#.get(key, 0) #2+: 0
'P29': {0: 0.3, 1: 0}#.get(key, 0) #2+: 0
'P30': {0: 0.3, 1: 0}#.get(key, 0) #2+: 0
'P31': {0: 0.3, 1: 0}#.get(key, 0) #2+: 0
'P32': {0: 0.3, 1: 0}#.get(key, 0) #2+: 0
'P33': {0: 0.5, 1: 0}#.get(key, 0) #2+: 0
'P34': {0: 0, 1: 1}#.get(key, 0) #1+: 1
}
##Funciones
p3 = lambda n: p3_d.get(n)
p11 = lambda n: p11_d.get(n,0)
p12 = lambda n: p12_d.get(n)
p13A
funciones = [p11,p12,p13A, None, p]
#Columnas
##Metatransform
map(lambda x,y:x(y), functions, values)
In [153]:
df = pd.read_excel('INMUEBLES.xlsx')
In [11]:
len(df[df['P12']>1]['P12'])
Out[11]:
In [82]:
df2=df[df['P3']<6]
len(df2['P3'])
Out[82]:
In [94]:
df2.ix[(df['P22']==3) & (df['P20']==3),'P20']=0
In [69]:
df2[(df['P22']==1) & (df['P20']==1)] #Estas respuestas no deberían tener sentido según el archivo de ponderaciones
Out[69]:
In [14]:
#Transformaciones
##Diccionarios
p3_d = {1:,2:,3:,4:,5:}
Out[14]:
In [8]:
df2[df2['P12']>2]
Out[8]:
In [45]:
df2['P11'].replace({0: 1, 1:1, 2:0},inplace=True)
In [84]:
#df2.ix[df2.P12<1, 'P12'] = 3
df2.ix[df2.P12>2, 'P12'] = 3
#df2[df2['P12']<1]['P12']
In [85]:
df2['P12'].replace({1: 1.5, 2: 1, 3: 0},inplace=True)
In [12]:
df2[df2['P13A']>4]
Out[12]:
In [13]:
#df2.ix[df2.P13A<1, 'P13A'] = 4
df2.ix[df2.P13A>4, 'P13A'] = 4
df2['P13A'].replace({1: 1.5, 2: 1, 3: 1, 4: 0},inplace=True)
#df2[df2['P13A']<1]['P13A']
In [63]:
#df2.ix[df2.P14<1, 'P14'] = 3
df2.ix[df2.P14>3, 'P14'] = 3
df2['P14'].replace({1: 3, 2: 2, 3: 0},inplace=True)
#df2[df2['P14']<1]['P14']
In [69]:
col='P15'
val = 4
df2.ix[df2.P15>val, col] = val
df2[col].replace({1: 3, 2: 2, 3: 2, 4: 0},inplace=True)
#print(max(df2[col]))
#print(min(df2[col]))
In [71]:
col='P16'
val = 3
df2.ix[df2.P16>val, col] = val
df2[col].replace({1: 3, 2: 2, 3: 0},inplace=True)
#print(max(df2[col]))
#print(min(df2[col]))
In [21]:
col='P17A'
val = 5
df2.ix[df2.P17A>val, col] = 4
df2[col].replace({1: 3, 2: 2, 3: 2, 4: 0, 5:1},inplace=True)
print(max(df2[col]))
print(min(df2[col]))
In [22]:
col='P18A'
val = 5
df2.ix[df2.P18A>val, col] = val
df2[col].replace({1: 3, 2: 2, 3: 2, 4: 1, 5:0},inplace=True)
print(max(df2[col]))
print(min(df2[col]))
In [23]:
col='P19'
val = 2
df2.ix[df2.P19>val, col] = val
df2[col].replace({1: 1, 2: 0},inplace=True)
print(max(df2[col]))
print(min(df2[col]))
In [86]:
col='P20'
val = 2
df2.ix[df2.P20>val, col] = val
df2[col].replace({1: 3, 2: 0},inplace=True)
print(max(df2[col]))
print(min(df2[col]))
df2[col].unique()
Out[86]:
In [25]:
col='P21'
val = 2
df2.ix[df2.P21>val, col] = val
df2[col].replace({1: 3, 2: 0},inplace=True)
print(max(df2[col]))
print(min(df2[col]))
In [26]:
col='P22'
val = 2
df2.ix[df2.P22>val, col] = val
df2[col].replace({1: 3, 2: 0},inplace=True)
print(max(df2[col]))
print(min(df2[col]))
In [81]:
col='P23'
val = 2
df2.ix[df2.P23>val, col] = val
df2[col].replace({1: 5.5, 2: 0},inplace=True)
print(max(df2[col]))
print(min(df2[col]))
In [83]:
col='P24'
val = 2
df2.ix[df2.P24>val, col] = val
df2[col].replace({1: 5.5, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [84]:
col='P25'
val = 2
df2.ix[df2.P25>val, col] = val
df2[col].replace({0: 0, 1: 0.5, 2: 1},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [85]:
col='P26'
val = 1
df2.ix[df2.P26>val, col] = val
#df2[col].replace({0: 0, 1: 1},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [86]:
col='P27'
val = 1
df2.ix[df2.P27>val, col] = val
#df2[col].replace({0: 0, 1: 1},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [87]:
col='P28'
val = 2
df2.ix[df2.P28>val, col] = val
df2[col].replace({0: 0.3, 1: 0, 2:0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [88]:
col='P29'
val = 2
df2.ix[df2.P29>val, col] = val
df2[col].replace({0: 0.3, 1: 0, 2:0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [89]:
col='P30'
val = 2
df2.ix[df2.P30>val, col] = val
df2[col].replace({0: 0.3, 1: 0, 2:0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [90]:
col='P31'
val = 2
df2.ix[df2.P31>val, col] = val
df2[col].replace({0: 0.3, 1: 0, 2:0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [91]:
col='P32'
val = 2
df2.ix[df2.P32>val, col] = val
df2[col].replace({0: 0.3, 1: 0, 2:0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [93]:
col='P33'
val = 2
df2.ix[df2.P33>val, col] = val
df2[col].replace({0: 0.5, 1: 0, 2:0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [94]:
col='P34'
val = 1
df2.ix[df2.P34>val, col] = val
#df2[col].replace({0: 0.3, 1: 0, 2:0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [95]:
col='P35'
val = 2
df2.ix[df2.P35>val, col] = val
df2[col].replace({0: 1.25, 1: 1, 2:0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [97]:
col='P36'
val = 1
df2.ix[df2.P36>val, col] = val
#df2[col].replace({0: 1.25, 1: 1, 2:0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [98]:
col='P37'
val = 2
df2.ix[df2.P37>val, col] = val
df2[col].replace({0: 1.25, 1: 1, 2:0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [99]:
col='P38'
val = 1
df2.ix[df2.P38>val, col] = val
#df2[col].replace({0: 1.25, 1: 1, 2:0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [100]:
col='P39'
val = 2
df2.ix[df2.P39>val, col] = val
df2[col].replace({0: 1.25, 1: 1, 2:0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [101]:
col='P40'
val = 1
df2.ix[df2.P40>val, col] = val
#df2[col].replace({0: 1.25, 1: 1, 2:0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [122]:
col='P41'
val = 2
df2.ix[df2.P41.isnull(), col] = 0
df2.ix[df2.P41>val, col] = val
df2[col].replace({0: 1.25, 1: 1, 2:0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [137]:
col='P42'
val = 3
df2.ix[df2.P42.isnull(), col] = 0
df2.ix[~(df2.P42>=val), col] = 0
df2.ix[df2.P42>=val, col] = 0.9
#df2[col].replace({0: 1.25, 1: 1, 2:0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [138]:
col='P44'
val = 1
df2.ix[df2.P44.isnull(), col] = 0
df2.ix[df2.P44>val, col] = val
df2[col].replace({0: 0, 1: 0.8},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [139]:
col='P46'
val = 1
df2.ix[df2.P46.isnull(), col] = 0
df2.ix[df2.P46>val, col] = val
df2[col].replace({0: 0, 1: 0.8},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [140]:
col='P47'
val = 1
df2.ix[df2.P47.isnull(), col] = 0
df2.ix[df2.P47>val, col] = val
df2[col].replace({0: 0, 1: 0.8},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [141]:
col='P48'
val = 1
df2.ix[df2.P48.isnull(), col] = 0
df2.ix[df2.P48>val, col] = val
df2[col].replace({0: 0, 1: 0.8},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [142]:
col='P49'
val = 1
df2.ix[df2.P49.isnull(), col] = 0
df2.ix[df2.P49>val, col] = val
df2[col].replace({0: 0, 1: 0.8},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [143]:
col='P52'
val = 1
df2.ix[df2.P52.isnull(), col] = 0
df2.ix[df2.P52>val, col] = val
df2[col].replace({0: 2, 1: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [144]:
col='P62'
val = 1
df2.ix[df2.P62.isnull(), col] = 0
df2.ix[df2.P62>val, col] = val
df2[col].replace({0: 2, 1: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [145]:
col='P72'
val = 1
df2.ix[df2.P72.isnull(), col] = 0
df2.ix[df2.P72>val, col] = val
df2[col].replace({0: 2, 1: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [146]:
col='P82'
val = 1
df2.ix[df2.P82.isnull(), col] = 0
df2.ix[df2.P82>val, col] = val
df2[col].replace({0: 2, 1: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [147]:
col='P92'
val = 1
df2.ix[df2.P92.isnull(), col] = 0
df2.ix[df2.P92>val, col] = val
df2[col].replace({0: 2, 1: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [148]:
col='P102'
val = 2
df2.ix[df2.P102.isnull(), col] = 0
df2.ix[df2.P102>val, col] = val
df2[col].replace({1: .25, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [150]:
col='P112'
val = 2
df2.ix[df2.P112.isnull(), col] = 0
df2.ix[df2.P112>val, col] = val
df2[col].replace({1: .25, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [151]:
col='P113'
val = 2
df2.ix[df2.P113.isnull(), col] = 0
df2.ix[df2.P113>val, col] = val
df2[col].replace({1: .25, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [152]:
col='P117'
val = 2
df2.ix[df2.P117.isnull(), col] = 0
df2.ix[df2.P117>val, col] = val
df2[col].replace({1: .25, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [153]:
col='P122'
val = 2
df2.ix[df2.P122.isnull(), col] = 0
df2.ix[df2.P122>val, col] = val
df2[col].replace({1: .25, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [154]:
col='P123'
val = 2
df2.ix[df2.P123.isnull(), col] = 0
df2.ix[df2.P123>val, col] = val
df2[col].replace({1: .25, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [155]:
col='P125'
val = 2
df2.ix[df2.P125.isnull(), col] = 0
df2.ix[df2.P125>val, col] = val
df2[col].replace({1: .25, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [156]:
col='P126'
val = 1
df2.ix[df2.P126.isnull(), col] = 0
df2.ix[df2.P126>val, col] = val
df2[col].replace({0: 0, 1: 2},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [158]:
col='P133'
val = 2
df2.ix[df2.P133.isnull(), col] = 0
df2.ix[df2.P133>val, col] = val
df2[col].replace({1: 1.2, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [159]:
col='P134'
val = 2
df2.ix[df2.P134.isnull(), col] = 0
df2.ix[df2.P134>val, col] = val
df2[col].replace({1: 1.2, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [160]:
col='P135'
val = 2
df2.ix[df2.P135.isnull(), col] = 0
df2.ix[df2.P135>val, col] = val
df2[col].replace({1: 1.2, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [161]:
col='P136'
val = 2
df2.ix[df2.P136.isnull(), col] = 0
df2.ix[df2.P136>val, col] = val
df2[col].replace({1: 1.2, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [162]:
col='P137'
val = 2
df2.ix[df2.P137.isnull(), col] = 0
df2.ix[df2.P137>val, col] = val
df2[col].replace({1: 1.2, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [163]:
col='P138'
val = 2
df2.ix[df2.P138.isnull(), col] = 0
df2.ix[df2.P138>val, col] = val
df2[col].replace({1: 1.2, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [164]:
col='P139'
val = 2
df2.ix[df2.P139.isnull(), col] = 0
df2.ix[df2.P139>val, col] = val
df2[col].replace({1: 1.2, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [165]:
col='P140'
val = 2
df2.ix[df2.P140.isnull(), col] = 0
df2.ix[df2.P140>val, col] = val
df2[col].replace({1: 1.2, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [167]:
col='P141'
val = 2
df2.ix[df2.P141.isnull(), col] = 0
df2.ix[df2.P141>val, col] = val
df2[col].replace({1: 0.4, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [168]:
col='P142'
val = 2
df2.ix[df2.P142.isnull(), col] = 0
df2.ix[df2.P142>val, col] = val
df2[col].replace({1: 0.5, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [169]:
col='P143'
val = 2
df2.ix[df2.P143.isnull(), col] = 0
df2.ix[df2.P143>val, col] = val
df2[col].replace({1: 0.5, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [170]:
col='P144'
val = 2
df2.ix[df2.P144.isnull(), col] = 0
df2.ix[df2.P144>val, col] = val
df2[col].replace({1: 4, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [171]:
col='P145'
val = 2
df2.ix[df2.P145.isnull(), col] = 0
df2.ix[df2.P145>val, col] = val
df2[col].replace({1: 4, 2: 0},inplace=True)
print(len(df2[df[col]<0]))
print(max(df2[col]))
print(min(df2[col]))
In [72]:
df2.to_csv('infraestuctura.csv')
In [71]:
print("nan:\t",len(df3[df3['P12'].isnull()]))
print("0:\t",len(df3[df3['P12']==0]))
print("1:\t",len(df3[df3['P12']==1]))
print(">2:\t",len(df3[df3['P12']>2]))
print("total:\t", len(df3['P12']))
In [65]:
len(df3[df3['P12'].isnull()])
Out[65]:
In [88]:
pd.Series(df3['P12'].values.ravel()).unique()
Out[88]:
In [52]:
from numpy import nan
In [93]:
df3 = df[df['P3']<6]
In [86]:
len(df3['P12'])
Out[86]:
In [87]:
df3.ix[df3.P12>3, 'P12'] = 3
In [91]:
len(df3[df3['P12']==3])
Out[91]:
In [105]:
print("nan:\t",len(df3[df3['P12'].isnull()]))
print("1:\t",len(df3[df3['P12']==1]))
print("2:\t",len(df3[df3['P12']==2]))
print("3:\t",len(df3[df3['P12']==3]))
print("total:\t", len(df3['P12']))
In [95]:
df3.ix[df3.P12<1, 'P12'] = 3
df3.ix[df3.P12>2, 'P12'] = 3
In [98]:
df3['P12'].replace({1: 1.5, 1: 1, 3: 0},inplace=True)
In [88]:
df2['P12']
Out[88]:
In [103]:
len(df3[df3['P12']==0])
Out[103]:
In [113]:
len(df[df['P12'].isnull()])
Out[113]:
In [114]:
infr = pd.read_csv("infraestructura.csv")
In [115]:
print("nan:\t",len(infr[infr['P12'].isnull()]))
print("0:\t",len(infr[infr['P12']==0]))
print("1:\t",len(infr[infr['P12']==1]))
print("2:\t",len(infr[infr['P12']==2]))
print("total:\t", len(infr['P12']))
In [90]:
print("nan:\t",len(df3[df3['P12'].isnull()]))
print("1:\t",len(df3[df3['P12']==1]))
print("2:\t",len(df3[df3['P12']==2]))
print("3:\t",len(df3[df3['P12']==3]))
print("total:\t", len(df3['P12']))
In [136]:
dif = infr['P12']==df3['P12']
In [129]:
dif.value()
In [143]:
lst=[]
s=0
for e in dif:
s+=1
if e==False:
lst.append(s)
In [127]:
secciones = [['P3'], ['P11', 'P12', 'P13A', 'P14', 'P15', 'P16'], ['P17A', 'P18A', 'P19', 'P20', 'P21', 'P22'], ['P23', 'P24'], ['P25', 'P26', 'P27', 'P28', 'P29', 'P30', 'P31', 'P32', 'P33', 'P34', 'P35', 'P36', 'P37', 'P38', 'P39', 'P40', 'P41'], ['P42', 'P44', 'P46', 'P47', 'P48', 'P49', 'P52', 'P62', 'P72', 'P82', 'P92', 'P102', 'P103', 'P112', 'P113', 'P117', 'P122', 'P123', 'P125'], ['P126'], ['P133', 'P134', 'P135', 'P136', 'P137', 'P138', 'P139', 'P140', 'P141', 'P142', 'P143'], ['P144', 'P145']]
max_cal = [11, 13, 13, 11, 14, 17, 2, 11, 8]
In [75]:
#print(secciones[2][0],":\t",df4[secciones[2][0]].max())
#print(secciones[2][1],":\t",df4[secciones[2][1]].max())
#print(secciones[2][2],":\t",df4[secciones[2][2]].max())
#print(secciones[2][3],":\t",df4[secciones[2][3]].max())
df4[secciones[2]].sum(axis=1)
Out[75]:
In [76]:
infr = pd.read_csv("infraestructura.csv")
In [99]:
infr.ix[:,'P12'] = df2.ix[:,'P12']
infr.ix[:,'P20'] = df2.ix[:,'P20']
In [137]:
infr.to_csv('infraestuctura.csv')
In [98]:
infr['P12'].unique()
Out[98]:
In [116]:
infr.ix[(infr['P20']==3) & (infr['P22']==3),'P20']=0
In [118]:
sec_lst
In [149]:
for j in range(9):
tmp=infr[secciones[j]].sum(axis=1).max()
print("Sección:", j+1,"\t",tmp, "<=", max_cal[j], "\t\t", tmp<=max_cal[j])
In [150]:
infr[secciones]
In [ ]: