from Notebooks.LinkDatabases.FacebookData import FacebookDataDatabase
import pandas as pd
import numpy as np
fbDatabase = FacebookDataDatabase()
counts = list(map(lambda x: x[0] if x[0] > 0 else 0, fbDatabase.selectColumnData("commentCount")))
for x in counts[:100]:
print(x)
df = pd.DataFrame(counts, columns=["commentCount"])
df.to_csv("comment_counts.csv")
from Notebooks.LinkDatabases.FacebookData import FacebookDataDatabase
facebookDb = FacebookDataDatabase()
shareCountsTuples = facebookDb.selectColumnData("shareCount")
shareCounts = list(map(lambda x: x[0], shareCountsTuples))
import numpy as np
from matplotlib import pyplot as plt
# fixed bin size
bins = np.arange(0, 100, 1) # fixed bin size
plt.xlim([min(shareCounts), 100])
plt.hist(shareCounts, bins=bins, alpha=0.5)
plt.savefig(
'/Users/ccrowe/Documents/Thesis/facebook_api/Notebooks/DataStats/shareCountHist.png'
)
print(np.std(shareCounts))
print(np.var(shareCounts))
from Notebooks.LinkDatabases.FacebookData import FacebookDataDatabase
import matplotlib.pyplot as plt
facebookDb = FacebookDataDatabase()
commentCounts = list(
map(lambda x: x[0], facebookDb.selectColumnData("shareCount")))[:5000]
plt.hist(commentCounts, bins=5000) # arguments are passed to np.histogram
plt.xlim(0, 200)
plt.title("Histogram of Share Counts")
plt.xlabel("Share Count")
plt.ylabel("Count")
plt.savefig(
"/Users/ccrowe/Documents/Thesis/facebook_api/Notebooks/shareCountHistogram.png"
)
from Notebooks.LinkDatabases.FacebookData import FacebookDataDatabase
import matplotlib.pyplot as plt
facebookDb = FacebookDataDatabase()
commentCounts = list(
filter(lambda x: x > -1,
map(lambda x: x[0], facebookDb.selectColumnData("postPositivity"))))
plt.hist(commentCounts, bins=100) # arguments are passed to np.histogram
plt.title("Histogram of Post Sentiment Positivity")
plt.xlabel("Post Sentiment")
plt.ylabel("Bin Count")
plt.savefig(
"/Users/ccrowe/Documents/Thesis/facebook_api/Notebooks/postSentimentHistogram.png"
)
from Notebooks.LinkDatabases.FacebookData import FacebookDataDatabase
import matplotlib.pyplot as plt
facebookDb = FacebookDataDatabase()
commentCounts = list(
map(lambda x: x[0], facebookDb.selectColumnData("commentCount")))
plt.hist(commentCounts, bins=2000) # arguments are passed to np.histogram
plt.xlim(0, 150)
plt.title("Histogram of Comment Counts")
plt.xlabel("Comment Count")
plt.ylabel("Count in Bin")
plt.savefig(
"/Users/ccrowe/Documents/Thesis/facebook_api/Notebooks/commentCountHistogram.png"
)
from Notebooks.LinkDatabases.FacebookData import FacebookDataDatabase
facebookDb = FacebookDataDatabase()
sentimentsTuples = facebookDb.selectColumnData("postPositivity")
sentiments = list(map(lambda x: x[0], sentimentsTuples))
import numpy as np
from matplotlib import pyplot as plt
# fixed bin size
bins = np.arange(0, 100, 1) # fixed bin size
plt.xlim([min(sentiments), 100])
plt.hist(sentiments, bins=bins, alpha=0.5)
plt.savefig(
'/Users/ccrowe/Documents/Thesis/facebook_api/Notebooks/DataStats/sentimentHist.png'
)
print(np.std(sentiments))
print(np.var(sentiments))
from Notebooks.LinkDatabases.FacebookData import FacebookDataDatabase
from Notebooks.LinkDatabases.PostComments import PostDataDatabase
import numpy as np
facebookDb = FacebookDataDatabase()
commentDb = PostDataDatabase()
commentCounts = facebookDb.selectColumnData("commentCount")
print("Comment Count Variance: {0}".format(np.var(commentCounts)))
shareCounts = facebookDb.selectColumnData("shareCount")
print("Share Count Variance: {0}".format(np.var(shareCounts)))
sentiments = list(map(lambda x: x[0] * 100, facebookDb.selectColumnData("postPositivity")))
print(sentiments[:20])
print("Sentiment Variance: {0}".format(np.var(sentiments)))
from Notebooks.LinkDatabases.FacebookData import FacebookDataDatabase
import numpy as np
facebookDb = FacebookDataDatabase()
commentCountsTuples = facebookDb.selectColumnData("commentCount")
commentCounts = list(map(lambda x: x[0], commentCountsTuples))
commentCountsLog = list(map(lambda x: np.log(x)
if x > 0 else x, commentCounts))
import numpy as np
from matplotlib import pyplot as plt
# fixed bin size
bins = np.arange(0, 100, 1) # fixed bin size
plt.xlim([min(commentCountsLog), 100])
plt.hist(commentCountsLog, bins=bins, alpha=0.5)
plt.savefig(
'/Users/ccrowe/Documents/Thesis/facebook_api/Notebooks/DataStats/commentCountHist.png'
)
print(np.std(commentCountsLog))
print(np.var(commentCountsLog))
