Importação de Libs, Dados e Definição de Diretório

import os                        # interact with system
import numpy             as np   # manipulation
import pandas            as pd   # manipulation
import statsmodels       as stm  # statistics
import seaborn           as sea  # visualization
#import matplotlib       as mpl  #      "
import matplotlib.pyplot as plt  #      "


# change working directory
os.chdir("/home/heitor/ProjetosPy/ML_PyPratice/Basic")

# import the csv file as "dd"
dd = pd.read_csv("pokemon.csv")

1) View Raw Data

dd                              # general

	name	type1	hp	attack	defense
793	Buzzwole	bug	107	139	139
468	Yanmega	bug	86	76	86
636	Volcarona	bug	85	60	65
213	Heracross	bug	80	185	115
616	Accelgor	bug	80	70	40
...	...	...	...	...	...
97	Krabby	water	30	105	90
115	Horsea	water	30	40	70
119	Staryu	water	30	45	55
128	Magikarp	water	20	10	55
348	Feebas	water	20	15	20

801 rows × 5 columns

dd.head(5)                      # first 5 lines

	abilities	against_bug	against_dark	against_dragon	against_electric	against_fairy	against_fight	against_fire	against_flying	against_ghost	...	percentage_male	pokedex_number	sp_attack	sp_defense	speed	type1	type2	weight_kg	generation	is_legendary
0	['Overgrow', 'Chlorophyll']	1.0	1.0	1.0	0.5	0.5	0.5	2.0	2.0	1.0	...	88.1	1	65	65	45	grass	poison	6.9	1	0
1	['Overgrow', 'Chlorophyll']	1.0	1.0	1.0	0.5	0.5	0.5	2.0	2.0	1.0	...	88.1	2	80	80	60	grass	poison	13.0	1	0
2	['Overgrow', 'Chlorophyll']	1.0	1.0	1.0	0.5	0.5	0.5	2.0	2.0	1.0	...	88.1	3	122	120	80	grass	poison	100.0	1	0
3	['Blaze', 'Solar Power']	0.5	1.0	1.0	1.0	0.5	1.0	0.5	1.0	1.0	...	88.1	4	60	50	65	fire	NaN	8.5	1	0
4	['Blaze', 'Solar Power']	0.5	1.0	1.0	1.0	0.5	1.0	0.5	1.0	1.0	...	88.1	5	80	65	80	fire	NaN	19.0	1	0

5 rows × 41 columns

dd["abilities"][0:7]            # spec variable and lines

0    ['Overgrow', 'Chlorophyll']
1    ['Overgrow', 'Chlorophyll']
2    ['Overgrow', 'Chlorophyll']
3       ['Blaze', 'Solar Power']
4       ['Blaze', 'Solar Power']
5       ['Blaze', 'Solar Power']
6       ['Torrent', 'Rain Dish']
Name: abilities, dtype: object

dd[["speed", "name", "type1"]]  # list spec variables

	speed	name	type1
0	45	Bulbasaur	grass
1	60	Ivysaur	grass
2	80	Venusaur	grass
3	65	Charmander	fire
4	80	Charmeleon	fire
...	...	...	...
796	61	Celesteela	steel
797	109	Kartana	grass
798	43	Guzzlord	dark
799	79	Necrozma	psychic
800	65	Magearna	steel

801 rows × 3 columns

dd.columns  # see col titles

Index(['abilities', 'against_bug', 'against_dark', 'against_dragon',
       'against_electric', 'against_fairy', 'against_fight', 'against_fire',
       'against_flying', 'against_ghost', 'against_grass', 'against_ground',
       'against_ice', 'against_normal', 'against_poison', 'against_psychic',
       'against_rock', 'against_steel', 'against_water', 'attack',
       'base_egg_steps', 'base_happiness', 'base_total', 'capture_rate',
       'classfication', 'defense', 'experience_growth', 'height_m', 'hp',
       'japanese_name', 'name', 'percentage_male', 'pokedex_number',
       'sp_attack', 'sp_defense', 'speed', 'type1', 'type2', 'weight_kg',
       'generation', 'is_legendary'],
      dtype='object')

dd.dtypes   # see col variables types

abilities             object
against_bug          float64
against_dark         float64
against_dragon       float64
against_electric     float64
against_fairy        float64
against_fight        float64
against_fire         float64
against_flying       float64
against_ghost        float64
against_grass        float64
against_ground       float64
against_ice          float64
against_normal       float64
against_poison       float64
against_psychic      float64
against_rock         float64
against_steel        float64
against_water        float64
attack                 int64
base_egg_steps         int64
base_happiness         int64
base_total             int64
capture_rate          object
classfication         object
defense                int64
experience_growth      int64
height_m             float64
hp                     int64
japanese_name         object
name                  object
percentage_male      float64
pokedex_number         int64
sp_attack              int64
sp_defense             int64
speed                  int64
type1                 object
type2                 object
weight_kg            float64
generation             int64
is_legendary           int64
dtype: object

dd.describe()

	against_bug	against_dark	against_dragon	against_electric	against_fairy	against_fight	against_fire	against_flying	against_ghost	against_grass	...	height_m	hp	percentage_male	pokedex_number	sp_attack	sp_defense	speed	weight_kg	generation	is_legendary
count	801.000000	801.000000	801.000000	801.000000	801.000000	801.000000	801.000000	801.000000	801.000000	801.000000	...	781.000000	801.000000	703.000000	801.000000	801.000000	801.000000	801.000000	781.000000	801.000000	801.000000
mean	0.996255	1.057116	0.968789	1.073970	1.068976	1.065543	1.135456	1.192884	0.985019	1.034020	...	1.163892	68.958801	55.155761	401.000000	71.305868	70.911361	66.334582	61.378105	3.690387	0.087391
std	0.597248	0.438142	0.353058	0.654962	0.522167	0.717251	0.691853	0.604488	0.558256	0.788896	...	1.080326	26.576015	20.261623	231.373075	32.353826	27.942501	28.907662	109.354766	1.930420	0.282583
min	0.250000	0.250000	0.000000	0.000000	0.250000	0.000000	0.250000	0.250000	0.000000	0.250000	...	0.100000	1.000000	0.000000	1.000000	10.000000	20.000000	5.000000	0.100000	1.000000	0.000000
25%	0.500000	1.000000	1.000000	0.500000	1.000000	0.500000	0.500000	1.000000	1.000000	0.500000	...	0.600000	50.000000	50.000000	201.000000	45.000000	50.000000	45.000000	9.000000	2.000000	0.000000
50%	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	...	1.000000	65.000000	50.000000	401.000000	65.000000	66.000000	65.000000	27.300000	4.000000	0.000000
75%	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000	2.000000	1.000000	1.000000	1.000000	...	1.500000	80.000000	50.000000	601.000000	91.000000	90.000000	85.000000	64.800000	5.000000	0.000000
max	4.000000	4.000000	2.000000	4.000000	4.000000	4.000000	4.000000	4.000000	4.000000	4.000000	...	14.500000	255.000000	100.000000	801.000000	194.000000	230.000000	180.000000	999.900000	7.000000	1.000000

8 rows × 34 columns

dd["speed"].describe()

count    801.000000
mean      66.334582
std       28.907662
min        5.000000
25%       45.000000
50%       65.000000
75%       85.000000
max      180.000000
Name: speed, dtype: float64

Lets see the strings variables:

dd["abilities"].describe()  # freq: most common value’s frequency

	name	type1	hp	attack	defense
793	Buzzwole	bug	107	139	139
468	Yanmega	bug	86	76	86
636	Volcarona	bug	85	60	65
213	Heracross	bug	80	185	115
616	Accelgor	bug	80	70	40
...	...	...	...	...	...
97	Krabby	water	30	105	90
115	Horsea	water	30	40	70
119	Staryu	water	30	45	55
128	Magikarp	water	20	10	55
348	Feebas	water	20	15	20

801 rows × 5 columns

dd["classfication"].describe()

count                801
unique               588
top       Dragon Pokémon
freq                   8
Name: classfication, dtype: object

dd["capture_rate"].describe()  # 'capture_rate' should be an int!!

count     801
unique     34
top        45
freq      250
Name: capture_rate, dtype: object

dd['is_legendary']  .value_counts()

0    731
1     70
Name: is_legendary, dtype: int64

dd["type1"].value_counts()

water       114
normal      105
grass        78
bug          72
psychic      53
fire         52
rock         45
electric     39
poison       32
ground       32
dark         29
fighting     28
ghost        27
dragon       27
steel        24
ice          23
fairy        18
flying        3
Name: type1, dtype: int64

dd["type2"].value_counts()

flying      95
poison      34
ground      34
fairy       29
psychic     29
fighting    25
steel       22
dark        21
grass       20
water       17
dragon      17
ice         15
rock        14
ghost       14
fire        13
electric     9
bug          5
normal       4
Name: type2, dtype: int64

Sorting:

dd.sort_values(by=["type1", "hp"],
               ascending=[1, 0])  # ascending by type1 but not by hp

	abilities	against_bug	against_dark	against_dragon	against_electric	against_fairy	against_fight	against_fire	against_flying	against_ghost	...	percentage_male	pokedex_number	sp_attack	sp_defense	speed	type1	type2	weight_kg	generation	is_legendary
793	['Beast Boost']	0.5	0.5	1.0	1.0	2.0	0.50	2.0	4.0	1.0	...	NaN	794	53	53	79	bug	fighting	333.6	7	1
468	['Speed Boost', 'Tinted Lens', 'Frisk']	0.5	1.0	1.0	2.0	1.0	0.25	2.0	2.0	1.0	...	50.0	469	116	56	95	bug	flying	51.5	4	0
636	['Flame Body', 'Swarm']	0.5	1.0	1.0	1.0	0.5	0.50	1.0	2.0	1.0	...	50.0	637	135	105	100	bug	fire	46.0	5	0
213	['Swarm', 'Guts', 'Moxie']	0.5	0.5	1.0	1.0	2.0	0.50	2.0	4.0	1.0	...	50.0	214	40	105	75	bug	fighting	54.0	2	0
616	['Hydration', 'Sticky Hold', 'Unburden']	1.0	1.0	1.0	1.0	1.0	0.50	2.0	2.0	1.0	...	50.0	617	100	60	145	bug	NaN	25.3	5	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
97	['Hyper Cutter', 'Shell Armor', 'Sheer Force']	1.0	1.0	1.0	2.0	1.0	1.00	0.5	1.0	1.0	...	50.0	98	25	25	50	water	NaN	6.5	1	0
115	['Swift Swim', 'Sniper', 'Damp']	1.0	1.0	1.0	2.0	1.0	1.00	0.5	1.0	1.0	...	50.0	116	70	25	60	water	NaN	8.0	1	0
119	['Illuminate', 'Natural Cure', 'Analytic']	1.0	1.0	1.0	2.0	1.0	1.00	0.5	1.0	1.0	...	NaN	120	70	55	85	water	NaN	34.5	1	0
128	['Swift Swim', 'Rattled']	1.0	1.0	1.0	2.0	1.0	1.00	0.5	1.0	1.0	...	50.0	129	15	20	80	water	NaN	10.0	1	0
348	['Swift Swim', 'Oblivious', 'Adaptability']	1.0	1.0	1.0	2.0	1.0	1.00	0.5	1.0	1.0	...	50.0	349	10	55	80	water	NaN	7.4	3	0

801 rows × 41 columns

dd[["name", "type1", "hp", "attack", "defense"]].sort_values(
    by=["type1", "hp"], ascending=[1, 0])

	name	type1	hp	attack	defense
793	Buzzwole	bug	107	139	139
468	Yanmega	bug	86	76	86
636	Volcarona	bug	85	60	65
213	Heracross	bug	80	185	115
616	Accelgor	bug	80	70	40
...	...	...	...	...	...
97	Krabby	water	30	105	90
115	Horsea	water	30	40	70
119	Staryu	water	30	45	55
128	Magikarp	water	20	10	55
348	Feebas	water	20	15	20

801 rows × 5 columns

2) Changing Data

modify the type of 'capture_rate':

dd["capture_rate"]  .astype(int)
dd.loc[dd['capture_rate'] == '30 (Meteorite)255 (Core)']

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
/tmp/ipykernel_23112/14930470.py in <module>
----> 1 dd["capture_rate"]  .astype(int)
      2 dd.loc[dd['capture_rate'] == '30 (Meteorite)255 (Core)']

~/.anaconda3/lib/python3.9/site-packages/pandas/core/generic.py in astype(self, dtype, copy, errors)
   5813         else:
   5814             # else, only a single dtype is given
-> 5815             new_data = self._mgr.astype(dtype=dtype, copy=copy, errors=errors)
   5816             return self._constructor(new_data).__finalize__(self, method="astype")
   5817 

~/.anaconda3/lib/python3.9/site-packages/pandas/core/internals/managers.py in astype(self, dtype, copy, errors)
    416 
    417     def astype(self: T, dtype, copy: bool = False, errors: str = "raise") -> T:
--> 418         return self.apply("astype", dtype=dtype, copy=copy, errors=errors)
    419 
    420     def convert(

~/.anaconda3/lib/python3.9/site-packages/pandas/core/internals/managers.py in apply(self, f, align_keys, ignore_failures, **kwargs)
    325                     applied = b.apply(f, **kwargs)
    326                 else:
--> 327                     applied = getattr(b, f)(**kwargs)
    328             except (TypeError, NotImplementedError):
    329                 if not ignore_failures:

~/.anaconda3/lib/python3.9/site-packages/pandas/core/internals/blocks.py in astype(self, dtype, copy, errors)
    589         values = self.values
    590 
--> 591         new_values = astype_array_safe(values, dtype, copy=copy, errors=errors)
    592 
    593         new_values = maybe_coerce_values(new_values)

~/.anaconda3/lib/python3.9/site-packages/pandas/core/dtypes/cast.py in astype_array_safe(values, dtype, copy, errors)
   1307 
   1308     try:
-> 1309         new_values = astype_array(values, dtype, copy=copy)
   1310     except (ValueError, TypeError):
   1311         # e.g. astype_nansafe can fail on object-dtype of strings

~/.anaconda3/lib/python3.9/site-packages/pandas/core/dtypes/cast.py in astype_array(values, dtype, copy)
   1255 
   1256     else:
-> 1257         values = astype_nansafe(values, dtype, copy=copy)
   1258 
   1259     # in pandas we don't store numpy str dtypes, so convert to object

~/.anaconda3/lib/python3.9/site-packages/pandas/core/dtypes/cast.py in astype_nansafe(arr, dtype, copy, skipna)
   1172         # work around NumPy brokenness, #1987
   1173         if np.issubdtype(dtype.type, np.integer):
-> 1174             return lib.astype_intsafe(arr, dtype)
   1175 
   1176         # if we have a datetime/timedelta array of objects

~/.anaconda3/lib/python3.9/site-packages/pandas/_libs/lib.pyx in pandas._libs.lib.astype_intsafe()

ValueError: invalid literal for int() with base 10: '30 (Meteorite)255 (Core)'

there's an observation in 'capture_rate' thar have a text, lets change this observ to 30+255 = 285:

dd.loc[dd['capture_rate'] == '30 (Meteorite)255 (Core)', 'capture_rate'] = '285'

now we can aplly the tranformation to int:

dd["capture_rate"] = dd["capture_rate"].astype(int)

transforming some variables in categorical:

dd["generation"]   = dd["generation"]   .astype('category')
dd["is_legendary"] = dd["is_legendary"] .astype('category')
dd["type1"]        = dd["type1"]        .astype('category')
dd["type2"]        = dd["type2"]        .astype('category')

Create a new variable: normality of Attack among generation subgroups: (var - var.min) / (var.max - var.min)

dd.groupby('generation')['attack'].min()
dd.groupby('generation')['attack'].max()

generation
1    155
2    185
3    180
4    170
5    150
6    160
7    181
Name: attack, dtype: int64

to this, we need a same length vector containing min & max of the generations:

dd.groupby('generation')['attack'].transform(min)

0       5
1       5
2       5
3       5
4       5
       ..
796    29
797    29
798    29
799    29
800    29
Name: attack, Length: 801, dtype: int64

dd.groupby('generation')['attack'].transform(max)

0      155
1      155
2      155
3      155
4      155
      ... 
796    181
797    181
798    181
799    181
800    181
Name: attack, Length: 801, dtype: int64

so:

dd['atk_gen_dnorm'] = (dd['attack'] - dd.groupby('generation')['attack'].transform(min)) / (dd.groupby('generation')['attack'].transform(max) - dd.groupby('generation')['attack'].transform(min))

dd['atk_gen_dnorm'].describe()

count    801.000000
mean       0.415197
std        0.216498
min        0.000000
25%        0.257143
50%        0.393939
75%        0.560000
max        1.000000
Name: atk_gen_dnorm, dtype: float64

Creating new var: mean of the against_x variables:

dd["Against_M"] = dd.iloc[:, 1:18].mean(axis=1)

dd['Against_M'].describe()

count    801.000000
mean       1.057979
std        0.113671
min        0.720588
25%        0.985294
50%        1.029412
75%        1.117647
max        1.441176
Name: Against_M, dtype: float64

Creating new var from type1:

• water. ice -> Aqua
• normal. fighting -> Normal
• fire. dragon. electric -> Energy
• rock. steel. ground. grass. bug -> Earth
• dark. ghost. psychic. poison -> Dark
• fairy. flying -> Air

dd['group1'] = dd['type1'].astype('str')

dd.group1[(dd['type1']=='water') | (dd['type1']=='ice')] = 'aqua'
dd.group1[(dd['type1']=='normal') | (dd['type1']=='fighting')] = 'body'
dd.group1[(dd['type1']=='fire') | (dd['type1']=='dragon') |
          (dd['type1']=='electric')] = 'energy'
dd.group1[(dd['type1']=='rock') | (dd['type1']=='steel') |
          (dd['type1']=='ground') | (dd['type1']=='grass') |
          (dd['type1']=='bug')] = 'earth'
dd.group1[(dd['type1']=='dark') | (dd['type1']=='ghost') |
           (dd['type1']=='psychic') | (dd['type1']=='poison')] = 'dark'
dd.group1[(dd['type1']=='fairy') | (dd['type1']=='flying')] = 'air'

dd['group1'] = dd['group1'].astype('category')

/tmp/ipykernel_23112/2645664726.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  dd.group1[(dd['type1']=='water') | (dd['type1']=='ice')] = 'aqua'
/tmp/ipykernel_23112/2645664726.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  dd.group1[(dd['type1']=='normal') | (dd['type1']=='fighting')] = 'body'
/tmp/ipykernel_23112/2645664726.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  dd.group1[(dd['type1']=='fire') | (dd['type1']=='dragon') |
/tmp/ipykernel_23112/2645664726.py:5: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  dd.group1[(dd['type1']=='rock') | (dd['type1']=='steel') |
/tmp/ipykernel_23112/2645664726.py:8: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  dd.group1[(dd['type1']=='dark') | (dd['type1']=='ghost') |
/tmp/ipykernel_23112/2645664726.py:10: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  dd.group1[(dd['type1']=='fairy') | (dd['type1']=='flying')] = 'air'

dd['group1'].value_counts()

earth     251
dark      141
aqua      137
body      133
energy    118
air        21
Name: group1, dtype: int64

Deleting Variables:

dd = dd[dd.columns.drop(list(dd.filter(regex='against')))] # deleting with condition
dd = dd.drop(columns=["abilities"])
dd = dd.drop(columns=["classfication"])
dd = dd.drop(columns=["base_egg_steps"])
dd = dd.drop(columns=["base_happiness"])
dd = dd.drop(columns=["base_total"])
dd = dd.drop(columns=["height_m"])
dd = dd.drop(columns=["percentage_male"])
dd = dd.drop(columns=["pokedex_number"])
dd = dd.drop(columns=["sp_attack"])
dd = dd.drop(columns=["sp_defense"])
dd = dd.drop(columns=["japanese_name"])

3) Filtering Data

print(dd.iloc[5:10])  # some specific lines

   attack  capture_rate  defense  experience_growth  hp       name  speed  \
5     104            45       78            1059860  78  Charizard    100   
6      48            45       65            1059860  44   Squirtle     43   
7      63            45       80            1059860  59  Wartortle     58   
8     103            45      120            1059860  79  Blastoise     78   
9      30           255       35            1000000  45   Caterpie     45   

   type1   type2  weight_kg generation is_legendary  atk_gen_dnorm  Against_M  \
5   fire  flying       90.5          1            0       0.660000   0.970588   
6  water     NaN        9.0          1            0       0.286667   1.029412   
7  water     NaN       22.5          1            0       0.386667   1.029412   
8  water     NaN       85.5          1            0       0.653333   1.029412   
9    bug     NaN        2.9          1            0       0.166667   1.088235   

   group1  
5  energy  
6    aqua  
7    aqua  
8    aqua  
9   earth  

print(dd.loc[dd["type1"] == "fire"])  # some spec character

     attack  capture_rate  defense  experience_growth   hp         name  \
3        52            45       43            1059860   39   Charmander   
4        64            45       58            1059860   58   Charmeleon   
5       104            45       78            1059860   78    Charizard   
36       41           190       40            1000000   38       Vulpix   
37       67            75       75            1000000   73    Ninetales   
57       70           190       45            1250000   55    Growlithe   
58      110            75       80            1250000   90     Arcanine   
76       85           190       55            1000000   50       Ponyta   
77      100            60       70            1000000   65     Rapidash   
125      95            45       57            1000000   65       Magmar   
135     130            45       60            1000000   65      Flareon   
145     100             3       90            1250000   90      Moltres   
154      52            45       43            1059860   39    Cyndaquil   
155      64            45       58            1059860   58      Quilava   
156      84            45       78            1059860   78   Typhlosion   
217      40           190       40            1000000   40       Slugma   
218      50            75      120            1000000   60     Magcargo   
239      75            45       37            1000000   45        Magby   
243     115             3       85            1250000  115        Entei   
249     130             3       90            1250000  106        Ho-Oh   
254      60            45       40            1059860   45      Torchic   
255      85            45       60            1059860   60    Combusken   
256     160            45       80            1059860   80     Blaziken   
321      60           255       40            1000000   60        Numel   
322     120           150      100            1000000   70     Camerupt   
323      85            90      140            1000000   70      Torkoal   
389      58            45       44            1059860   44     Chimchar   
390      78            45       52            1059860   64     Monferno   
391     104            45       71            1059860   76    Infernape   
466      95            30       67            1000000   75    Magmortar   
484      90             3      106            1250000   91      Heatran   
497      63            45       45            1059860   65        Tepig   
498      93            45       55            1059860   90      Pignite   
499     123            45       65            1059860  110       Emboar   
512      53           190       48            1000000   50      Pansear   
513      98            75       63            1000000   75     Simisear   
553      90           120       45            1059860   70     Darumaka   
554      30            60      105            1059860  105   Darmanitan   
630      97            90       66            1000000   85      Heatmor   
652      45            45       40            1059860   40     Fennekin   
653      59            45       58            1059860   59      Braixen   
654      69            45       72            1059860   75      Delphox   
661      73           120       55            1059860   62  Fletchinder   
662      81            45       71            1059860   78   Talonflame   
666      50           220       58            1059860   62       Litleo   
667      68            65       72            1059860   86       Pyroar   
720     110             3      120            1250000   80    Volcanion   
724      65            45       40            1059860   45       Litten   
725      85            45       50            1059860   65     Torracat   
726     115            45       90            1059860   95   Incineroar   
740      70            45       70            1000000   75     Oricorio   
775      78            70      135            1000000   60   Turtonator   

     speed type1     type2  weight_kg generation is_legendary  atk_gen_dnorm  \
3       65  fire       NaN        8.5          1            0       0.313333   
4       80  fire       NaN       19.0          1            0       0.393333   
5      100  fire    flying       90.5          1            0       0.660000   
36      65  fire       ice        NaN          1            0       0.240000   
37     109  fire       ice        NaN          1            0       0.413333   
57      60  fire       NaN       19.0          1            0       0.433333   
58      95  fire       NaN      155.0          1            0       0.700000   
76      90  fire       NaN       30.0          1            0       0.533333   
77     105  fire       NaN       95.0          1            0       0.633333   
125     93  fire       NaN       44.5          1            0       0.600000   
135     65  fire       NaN       25.0          1            0       0.833333   
145     90  fire    flying       60.0          1            1       0.633333   
154     65  fire       NaN        7.9          2            0       0.240000   
155     80  fire       NaN       19.0          2            0       0.308571   
156    100  fire       NaN       79.5          2            0       0.422857   
217     20  fire       NaN       35.0          2            0       0.171429   
218     30  fire      rock       55.0          2            0       0.228571   
239     83  fire       NaN       21.4          2            0       0.371429   
243    100  fire       NaN      198.0          2            1       0.600000   
249     90  fire    flying      199.0          2            1       0.685714   
254     45  fire       NaN        2.5          3            0       0.272727   
255     55  fire  fighting       19.5          3            0       0.424242   
256    100  fire  fighting       52.0          3            0       0.878788   
321     35  fire    ground       24.0          3            0       0.272727   
322     20  fire    ground      220.0          3            0       0.636364   
323     20  fire       NaN       80.4          3            0       0.424242   
389     61  fire       NaN        6.2          4            0       0.321212   
390     81  fire  fighting       22.0          4            0       0.442424   
391    108  fire  fighting       55.0          4            0       0.600000   
466     83  fire       NaN       68.0          4            0       0.545455   
484     77  fire     steel      430.0          4            1       0.515152   
497     45  fire       NaN        9.9          5            0       0.304000   
498     55  fire  fighting       55.5          5            0       0.544000   
499     65  fire  fighting      150.0          5            0       0.784000   
512     64  fire       NaN       11.0          5            0       0.224000   
513    101  fire       NaN       28.0          5            0       0.584000   
553     50  fire       NaN       37.5          5            0       0.520000   
554     55  fire      fire       92.9          5            0       0.040000   
630     65  fire       NaN       58.0          5            0       0.576000   
652     60  fire       NaN        9.4          6            0       0.166667   
653     73  fire       NaN       14.5          6            0       0.268116   
654    104  fire   psychic       39.0          6            0       0.340580   
661     84  fire    flying       16.0          6            0       0.369565   
662    126  fire    flying       24.5          6            0       0.427536   
666     72  fire    normal       13.5          6            0       0.202899   
667    106  fire    normal       81.5          6            0       0.333333   
720     70  fire     water      195.0          6            1       0.637681   
724     70  fire       NaN        4.3          7            0       0.236842   
725     90  fire       NaN       25.0          7            0       0.368421   
726     60  fire      dark       83.0          7            0       0.565789   
740     93  fire    flying        3.4          7            0       0.269737   
775     36  fire    dragon      212.0          7            0       0.322368   

     Against_M  group1  
3     0.941176  energy  
4     0.941176  energy  
5     0.970588  energy  
36    0.941176  energy  
37    0.941176  energy  
57    0.941176  energy  
58    0.941176  energy  
76    0.941176  energy  
77    0.941176  energy  
125   0.941176  energy  
135   0.941176  energy  
145   0.970588  energy  
154   0.941176  energy  
155   0.941176  energy  
156   0.941176  energy  
217   0.941176  energy  
218   1.073529  energy  
239   0.941176  energy  
243   0.941176  energy  
249   0.970588  energy  
254   0.941176  energy  
255   0.985294  energy  
256   0.985294  energy  
321   0.852941  energy  
322   0.852941  energy  
323   0.941176  energy  
389   0.941176  energy  
390   0.985294  energy  
391   0.985294  energy  
466   0.941176  energy  
484   0.838235  energy  
497   0.941176  energy  
498   0.985294  energy  
499   0.985294  energy  
512   0.941176  energy  
513   0.941176  energy  
553   0.941176  energy  
554   0.941176  energy  
630   0.941176  energy  
652   0.941176  energy  
653   0.941176  energy  
654   1.029412  energy  
661   0.970588  energy  
662   0.970588  energy  
666   0.941176  energy  
667   0.941176  energy  
720   0.985294  energy  
724   0.941176  energy  
725   0.941176  energy  
726   0.941176  energy  
740   0.970588  energy  
775   1.000000  energy  

dd.loc[(dd["type1"] == "grass") & (dd["type2"] == "poison") & (dd["hp"] > 75)]

	attack	capture_rate	defense	experience_growth	hp	name	speed	type1	type2	weight_kg	generation	is_legendary	atk_gen_dnorm	Against_M	group1
2	100	45	123	1059860	80	Venusaur	80	grass	poison	100.0	1	0	0.633333	1.102941	earth
70	105	45	65	1059860	80	Victreebel	70	grass	poison	15.5	1	0	0.666667	1.102941	earth
590	85	75	70	1000000	114	Amoonguss	30	grass	poison	10.5	5	0	0.480000	1.102941	earth

Obs: iloc is purely by indexes and loc by names. Now, lets select what contains 'Mega' in name:

dd.loc[dd["name"].str.contains("mega")]

	attack	capture_rate	defense	experience_growth	hp	name	speed	type1	type2	weight_kg	generation	is_legendary	atk_gen_dnorm	Against_M	group1
468	76	30	86	1000000	86	Yanmega	95	bug	flying	51.5	4	0	0.430303	1.235294	earth

Select type fire or water:

dd.loc[dd["type1"].str.contains("fire|water")]

	attack	capture_rate	defense	experience_growth	hp	name	speed	type1	type2	weight_kg	generation	is_legendary	atk_gen_dnorm	Against_M	group1
3	52	45	43	1059860	39	Charmander	65	fire	NaN	8.5	1	0	0.313333	0.941176	energy
4	64	45	58	1059860	58	Charmeleon	80	fire	NaN	19.0	1	0	0.393333	0.941176	energy
5	104	45	78	1059860	78	Charizard	100	fire	flying	90.5	1	0	0.660000	0.970588	energy
6	48	45	65	1059860	44	Squirtle	43	water	NaN	9.0	1	0	0.286667	1.029412	aqua
7	63	45	80	1059860	59	Wartortle	58	water	NaN	22.5	1	0	0.386667	1.029412	aqua
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
751	70	100	92	1000000	68	Araquanid	42	water	bug	82.0	7	0	0.269737	1.058824	aqua
770	60	60	130	800000	55	Pyukumuku	5	water	NaN	1.2	7	0	0.203947	1.029412	aqua
775	78	70	135	1000000	60	Turtonator	36	fire	dragon	212.0	7	0	0.322368	1.000000	energy
778	105	80	70	1000000	68	Bruxish	92	water	psychic	19.0	7	0	0.500000	1.147059	aqua
787	75	3	115	1250000	70	Tapu Fini	85	water	fairy	21.2	7	1	0.302632	0.970588	aqua

166 rows × 15 columns

4) Grouping

dd.groupby("type1").mean().sort_values("attack")

	attack	capture_rate	defense	experience_growth	hp	speed	weight_kg	atk_gen_dnorm	Against_M
type1
fairy	62.111111	116.944444	68.166667	9.138889e+05	73.944444	53.666667	23.555556	0.305327	0.977124
psychic	65.566038	86.660377	69.264151	1.079405e+06	72.943396	75.150943	57.328846	0.323916	1.112375
flying	66.666667	79.333333	65.000000	1.083333e+06	68.000000	99.666667	52.000000	0.335266	1.117647
bug	70.125000	119.833333	70.847222	1.009006e+06	56.722222	63.569444	33.083333	0.361085	1.119077
electric	70.820513	106.974359	61.820513	1.073312e+06	60.512821	85.410256	37.944737	0.378562	0.952489
poison	72.656250	128.437500	70.031250	1.086849e+06	65.593750	64.187500	33.830000	0.399824	0.978860
ghost	72.740741	93.814815	79.518519	1.018117e+06	63.370370	58.333333	69.570370	0.365167	0.971678
ice	73.304348	94.173913	71.913043	1.086069e+06	72.086957	62.739130	103.260870	0.386124	1.201407
water	73.307018	99.412281	73.482456	1.056716e+06	70.219298	63.921053	51.071930	0.387995	1.043473
grass	73.769231	106.935897	70.871795	1.079791e+06	65.358974	59.025641	33.255844	0.379938	1.200792
normal	75.161905	120.219048	59.695238	1.009973e+06	76.723810	69.533333	46.158416	0.399823	1.005322
fire	81.500000	72.403846	67.788462	1.064735e+06	68.730769	73.346154	66.096000	0.439117	0.950509
dark	87.793103	84.482759	70.517241	1.102720e+06	72.551724	75.310345	69.096552	0.472996	1.080122
rock	90.666667	76.533333	96.266667	9.793116e+05	66.333333	57.422222	92.946341	0.505399	1.146078
steel	93.083333	58.916667	120.208333	1.126232e+06	66.791667	56.583333	188.841667	0.493987	0.841912
ground	94.812500	108.312500	83.906250	1.069652e+06	73.187500	59.968750	150.044444	0.540137	1.028493
fighting	99.178571	103.750000	66.392857	1.076021e+06	71.428571	64.285714	58.675000	0.571414	1.090336
dragon	106.407407	37.333333	86.259259	1.216667e+06	79.851852	76.111111	107.125926	0.604641	1.129085

5) Visualization with Seaborn:

sea.set()
g1  = sea.histplot(dd, x="attack")

g11 = sea.histplot(dd, x="attack", kde=True)

g2 = sea.relplot(x= 'attack', y='defense', data=dd)

g3 = sea.relplot(data=dd,
                 x= 'attack',
                 y='defense',
                 hue='group1')

g4 = sea.jointplot(data=dd,
                   x= 'attack',
                   y='defense',
                   hue='group1')

g41 = sea.jointplot(data=dd,
                   x= 'attack',
                   y='defense',
                   hue='is_legendary',
                   kind= 'kde')

g42 = sea.jointplot(data=dd,
                   x= 'attack',
                   y='defense',
                   #hue='is_legendary',
                   kind= 'reg')

g43 = sea.jointplot(data=dd,
                   x= 'attack',
                   y='defense',
                   #hue='is_legendary',
                   kind= 'hex')

g5 = sea.jointplot(data=dd,
                   y='hp',
                   x='capture_rate')
g5.plot_joint(sea.kdeplot,
              color='r',
              zorder=0,
              levels=6)
g5.plot_marginals(sea.rugplot,
                  color="r",
                  height=-.15,
                  clip_on=False)

<seaborn.axisgrid.JointGrid at 0x7fdb1c5b16a0>

g6 = sea.pairplot(dd[['attack', 'defense', 'hp', 'speed', 'group1']],
                  hue='group1', height=2.5)

sea.set_theme(style="ticks")
# Initialize the figure with a logarithmic x axis
f, ax = plt.subplots(figsize=(7, 6))
# Plot the orbital period with horizontal boxes
sea.boxplot(data=dd,
            y="group1",
            x="hp", 
            whis=[0, 100],
            width=.6,
            palette="Set3", showmeans=True) # the means are hidden by scarttes
# Add in points to show each observation
sea.stripplot(data=dd,
              y="group1",
              x="hp",
              size=4,
              color=".3",
              linewidth=0,
              alpha=.45)
# Tweak the visual presentation
ax.xaxis.grid(True)
ax.set(ylabel="Primary Type Group")
sea.despine(trim=True, left=True)

Rain Cloud:

 https://towardsdatascience.com/violin-strip-swarm-and-raincloud-plots-in-python-as-better-sometimes-alternatives-to-a-boxplot-15019bdff8f8

plt.figure(figsize=(15, 10))
# Create violin plots without mini-boxplots inside.
ax = sea.violinplot(data=dd,
                    x='speed',
                    y='group1',
                    color='paleturquoise', 
                    cut=0,
                    inner=None)
# Clip the lower half of each violin.
for item in ax.collections:
    x0, y0, width, height = item.get_paths()[0].get_extents().bounds
    item.set_clip_path(plt.Rectangle((x0, y0), width, height/2,
                       transform=ax.transData))
# Create [swarm vs strip] plots with partially transparent points of different colors depending if is legendary.
num_items = len(ax.collections)
sea.stripplot(data=dd,
              x='speed',
              y='group1',
              hue='is_legendary', 
              palette=['deepskyblue', 'navy'],
              alpha=0.6,
              size=7)
# Shift each strip plot strictly below the correponding volin.
for item in ax.collections[num_items:]:
    item.set_offsets(item.get_offsets() + 0.15)
# Create narrow boxplots on top of the corresponding violin and strip plots, with thick lines, the mean values, without the outliers.
sea.boxplot(data=dd,
            x='speed',
            y='group1',
            width=0.25,
            showfliers=False,
            showmeans=True, 
            meanprops=dict(marker='o', markerfacecolor='gold',
                           markersize=10, zorder=3),
            boxprops=dict(facecolor=(0,0,0,0), 
                          linewidth=3, zorder=3),
            whiskerprops=dict(linewidth=3),
            capprops=dict(linewidth=3),
            medianprops=dict(linewidth=3))
plt.legend(frameon=False, fontsize=15, loc='upper left')

<matplotlib.legend.Legend at 0x7fdb15f20220>