MariaLavrovskaya

#importing the libraries
import pandas as pd
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
import statsmodels.api as sm
%matplotlib inline
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression

MariaLavrovskaya

#importing the libraries
import pandas as pd
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
import statsmodels.api as sm
%matplotlib inline
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression

MariaLavrovskaya

#Using Pearson Correlation
plt.figure(figsize=(12,10))
cor = df.corr()
sns.heatmap(cor, annot=True, cmap=plt.cm.Reds)
plt.show()

MariaLavrovskaya

#Using Pearson Correlation
plt.figure(figsize=(12,10))
cor = df.corr()
sns.heatmap(cor, annot=True, cmap=plt.cm.Reds)
plt.show()

MariaLavrovskaya

df.set_index("title", inplace=True) #setting the index name
df_1 = df.loc[:, ['imdb_rating','genre', 'runtime', 'best_pic_nom',
                  'top200_box', 'director', 'actor1']]

MariaLavrovskaya

#Let's also check the column-wise distribution of null values
print(df_1.isnull().values.sum())
print(df_1.isnull().sum())

MariaLavrovskaya

#Dropping missing values from my dataset
df_1.dropna(how='any', inplace=True)
print(df_1.isnull().values.sum()) #checking for missing values after the dropna()

MariaLavrovskaya

#Treating categorical variables with One-hot-encoding
from sklearn import preprocessing
le = preprocessing.LabelEncoder()


# LabelEncoder for a number of columns
class MultiColumnLabelEncoder:

    def __init__(self, columns = None):
        self.columns = columns # list of column to encode

MariaLavrovskaya

#From labels to dummy
from sklearn.preprocessing import OneHotEncoder
ohe = OneHotEncoder(sparse=False)
X_train_ohe = ohe.fit_transform(X_train_le)

MariaLavrovskaya

#Treating continous variables with Standart Scaler

columns_to_scale = np.array(df_1['runtime'])
#Initiate Scaler:
scaler = StandardScaler()
scaled_columns  = scaler.fit_transform(columns_to_scale[:, np.newaxis])