Python Beginners(5) - Pandas_ind

1. Select Rows

# First five rows
fandango[0:5]
# From row at 140 and higher
fandango[140:]
# Just row at index 50
fandango.iloc[50]
# Just row at index 45 and 90
fandango.iloc[[45,90]]
# Select first and last row
fandango.iloc[[0,-1]]

2. Set index

fandango = pd.read_csv('fandango_score_comparison.csv')
fandango_films = fandango.set_index("FILM", inplace = False, drop = False)
print (fandango_films.index)

loc(index_names)

mlist = ["The Lazarus Effect (2015)", "Gett: The Trial of Viviane Amsalem (2015)", "Mr. Holmes (2015)"]
best_movies_ever = fandango_films.loc[mlist]
print (best_movies_ever)

3.Apply Functions

Apply functions.

import pandas as pd
import numpy as np

fandango_films = pd.read_csv("fandango_score_comparison.csv")
types = fandango_films.dtypes
print (types)

float_columns = types[types.values == "float64"].index
print (float_columns)

float_df = fandango_films[float_columns]

print (float_df)

deviations = float_df.apply(lambda x: np.std(x))
print (deviations)

4.Apply Functions along Rows

rt_mt_user = float_df[['RT_user_norm', 'Metacritic_user_nom']]
rt_mt_deviations = rt_mt_user.apply(lambda x: np.std(x), axis=1)
print(rt_mt_deviations[0:5])
rt_mt_means = rt_mt_user.apply(lambda x: np.mean(x), axis = 1)
print (rt_mt_means[0:5])