Learn practical skills, build real-world projects, and advance your career
# Python Imports
!pip install catboost
!pip install xgboost

import pandas as pd
import numpy as np # Linear Algebra
import random, time, datetime

# Data visualization
import matplotlib.pyplot as plt
import seaborn as sns

# Data Preprocessing
from sklearn.pipeline import Pipeline, make_pipeline
from sklearn.preprocessing import RobustScaler, MinMaxScaler, StandardScaler, OneHotEncoder
from sklearn.impute import SimpleImputer
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.decomposition import PCA

# Machine Learning
from sklearn import model_selection, tree, preprocessing, metrics
from sklearn import linear_model
from xgboost import XGBRegressor
from lightgbm import LGBMRegressor, LGBMClassifier
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import RandomForestRegressor
from sklearn.ensemble import AdaBoostRegressor
from catboost import Pool, CatBoostRegressor
from sklearn.svm import LinearSVC
from sklearn import svm
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import LogisticRegression, SGDClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from xgboost.sklearn import XGBClassifier
import xgboost as xgb

# Validation & Scoring
from sklearn.model_selection import cross_val_score, GridSearchCV, KFold
from sklearn import svm

from sklearn.model_selection import KFold, cross_val_score
from sklearn.metrics import accuracy_score, confusion_matrix, f1_score, mean_squared_error, make_scorer, mean_squared_error
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import train_test_split

sns.set_style("whitegrid")
%matplotlib inline
import warnings
warnings.filterwarnings("ignore")
Requirement already satisfied: catboost in /opt/conda/lib/python3.7/site-packages (0.23.2) Requirement already satisfied: numpy>=1.16.0 in /opt/conda/lib/python3.7/site-packages (from catboost) (1.18.5) Requirement already satisfied: matplotlib in /opt/conda/lib/python3.7/site-packages (from catboost) (3.2.1) Requirement already satisfied: graphviz in /opt/conda/lib/python3.7/site-packages (from catboost) (0.8.4) Requirement already satisfied: plotly in /opt/conda/lib/python3.7/site-packages (from catboost) (4.9.0) Requirement already satisfied: six in /opt/conda/lib/python3.7/site-packages (from catboost) (1.14.0) Requirement already satisfied: scipy in /opt/conda/lib/python3.7/site-packages (from catboost) (1.4.1) Requirement already satisfied: pandas>=0.24.0 in /opt/conda/lib/python3.7/site-packages (from catboost) (1.0.3) Requirement already satisfied: kiwisolver>=1.0.1 in /opt/conda/lib/python3.7/site-packages (from matplotlib->catboost) (1.2.0) Requirement already satisfied: cycler>=0.10 in /opt/conda/lib/python3.7/site-packages (from matplotlib->catboost) (0.10.0) Requirement already satisfied: python-dateutil>=2.1 in /opt/conda/lib/python3.7/site-packages (from matplotlib->catboost) (2.8.1) Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in /opt/conda/lib/python3.7/site-packages (from matplotlib->catboost) (2.4.7) Requirement already satisfied: retrying>=1.3.3 in /opt/conda/lib/python3.7/site-packages (from plotly->catboost) (1.3.3) Requirement already satisfied: pytz>=2017.2 in /opt/conda/lib/python3.7/site-packages (from pandas>=0.24.0->catboost) (2019.3) WARNING: You are using pip version 20.1.1; however, version 20.2 is available. You should consider upgrading via the '/opt/conda/bin/python3.7 -m pip install --upgrade pip' command. Requirement already satisfied: xgboost in /opt/conda/lib/python3.7/site-packages (1.1.1) Requirement already satisfied: numpy in /opt/conda/lib/python3.7/site-packages (from xgboost) (1.18.5) Requirement already satisfied: scipy in /opt/conda/lib/python3.7/site-packages (from xgboost) (1.4.1) WARNING: You are using pip version 20.1.1; however, version 20.2 is available. You should consider upgrading via the '/opt/conda/bin/python3.7 -m pip install --upgrade pip' command.
import os
for dirname, _, filenames in os.walk('/kaggle/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename))
/kaggle/input/american-bank-data/Bank_of_America_data.csv
american = pd.read_csv("/kaggle/input/american-bank-data/Bank_of_America_data.csv")

Exploratory Data Analysis

american.shape
(5960, 13)